US20100111377A1 - Method for Incorporating Facial Recognition Technology in a Multimedia Surveillance System - Google Patents
Method for Incorporating Facial Recognition Technology in a Multimedia Surveillance System Download PDFInfo
- Publication number
- US20100111377A1 US20100111377A1 US12/606,533 US60653309A US2010111377A1 US 20100111377 A1 US20100111377 A1 US 20100111377A1 US 60653309 A US60653309 A US 60653309A US 2010111377 A1 US2010111377 A1 US 2010111377A1
- Authority
- US
- United States
- Prior art keywords
- facial
- image data
- camera
- database
- signature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19647—Systems specially adapted for intrusion detection in or around a vehicle
- G08B13/1965—Systems specially adapted for intrusion detection in or around a vehicle the vehicle being an aircraft
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19654—Details concerning communication with a camera
- G08B13/19656—Network used to communicate with a camera, e.g. WAN, LAN, Internet
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19665—Details related to the storage of video surveillance data
- G08B13/19671—Addition of non-video data, i.e. metadata, to video stream
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19678—User interface
- G08B13/19682—Graphic User Interface [GUI] presenting system data to the user, e.g. information on a screen helping a user interacting with an alarm system
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19678—User interface
- G08B13/19691—Signalling events for better perception by user, e.g. indicating alarms by making display brighter, adding text, creating a sound
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/016—Personal emergency signalling and security systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/14—Central alarm receiver or annunciator arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/05—Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
- G07C2011/02—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere related to amusement parks
Definitions
- the invention generally relates to use of facial recognition technology as used in surveillance and access systems and is specifically directed to incorporation of such technology in an IP compatible, networked, comprehensive multimedia surveillance system.
- the FaceIt software measures a face according to its peaks and valleys—such as the tip of the nose, the depth of the eye sockets—which are known as nodal points.
- a typical human face has 80 nodal points and precise recognition can be achieved with as few as 14 to 22 utilizing the FaceIt system.
- the FaceIt system concentrates on the inner region of the face, which runs from temple to temple and just over the lip, called the ‘golden triangle.’ This is the most stable because even if facial hair such as a beard is altered, or if the subject changes or adds glasses, changes in weight or ages substantially the ‘golden triangle’ region tends to not be affected, while places such as under chin would be substantially altered. FaceIt plots the relative positions of these points and comes up with a long string of numbers, called a faceprint.
- Visage Technology of Littleton, Mass. has a slightly different model. Its software compares faces to 128 archetypes it has on record. Faces are then assigned numbers according to how they are similar or different from these models.
- the Visage Technology has been utilized to date in the identification of criminals, for access control, for transaction security and for identity fraud prevention.
- the facial recognition technology has several advantages over other biometric systems. For example, with facial recognition technology a person can be identified at a distance or in a crowd.
- the technology has the capability of capturing a face in the field of view, extract the face from the background data and compare it against a database.
- the system permits the creation of watch lists or the like. This could include, for example, known shoplifters, terrorists or criminals, as well as frequent customers, VIP's, expected visitors or individuals generally classified as friends or foes.
- the system can be used at airports, casinos, public buildings, schools, subways, colleges, factories, business facilities, housing complexes, residences and the like.
- the system also is useful in transaction modes.
- Customers are used to being verified or being recognized by their face at retail locations by providing merchants with a driver's license or other form of photo ID.
- signature verification process which is highly unreliable and cannot be accurately determined by unskilled and untrained clerks
- face recognition makes verification reliable, automatic and fast.
- facial recognition technology can adapt to already installed ATM cameras for recognizing and verifying customer identities so the financial transaction can be quickly and effortlessly conducted. Such technology can replace reliance on alphanumeric PINs to identify and authenticate a user.
- Face recognition is the only biometric that can be used in two modalities—logon and continuous monitoring.
- An example of logon modality is use as a perimeter defense mechanism, where an authorized individual gains entry to a network or session after a one-time logon process. This is the typical mode for all biometric systems.
- face recognition supports a continuous monitoring mode where persons are continuously authenticated for ensuring that at all times the individual in front of the computer or handheld device continues to be the same authorized person who logged in.
- Normalization The image of the head is scaled and rotated so that it can be registered and mapped into an appropriate size and pose. Normalization is performed regardless of the head's location and distance from the camera.
- the system translates the facial data into a unique code. This coding process allows for easier comparison of the newly acquired facial data to stored facial data.
- Matching The newly acquired facial data is compared to the stored data and linked to at least one stored facial representation.
- a camera views a scene of interest
- a processor analyzes the video signals produced by the camera.
- the processor performs the steps of:
- the basic function of the system can be enhanced by dividing the processing function processors.
- One or more processors perform the computationally intensive tasks of Facial Separation and Facial Signature generation, while yet another processor performs the less demanding task of database pattern matching. This yields improved system economies and flexibility.
- Cameras and Facial Processors may be added incrementally to the system as needed, and as is unnecessary for each Facial Processor to contain or to access the entire ‘reference’ database.
- the utility of the system may be enhanced by the increased use of the networking techniques of the subject invention.
- a group of networked processors perform the steps of Facial Separation and Facial Signature generation.
- the Facial Processors function as network resources, and are configured to process video from any networked camera, as required. This improves the flexibility and economics of the system. For example, during periods when a particular area is not used, Facial Processors may be diverted from analysis of that particular camera to an area of higher traffic. Also, the workload of a failed Facial Processor may be diverted to a different processor.
- the Facial Database may be treated as a general-purpose network resource, allowing a greater number of cameras and Facial Processors to perform Facial Signature lookups at any given time.
- the digital IP surveillance network is often part of a larger “network of networks”, thus allowing the Facial. Database to be consulted by devices on a different network. This is useful in cases where different organizations may have compiled different Facial Databases. For example, an airport may maintain a database of the Facial Signatures of all current employees, as well as of past employees. A law enforcement organization may maintain a separate database of known offenders, and an Intelligence organization may maintain a current database of foreign nationals of interest. In the depicted networked environment, the Facial Processors may consult several different Facial Databases, across the LAN or WAN.
- IP surveillance systems often maintain an archive of stored video or images. Since this archive is generally available on the network, it is possible to use the system to search for faces in archived images, during event reconstruction.
- the IP surveillance network stores captured images or video in an Image Database. Often, these images are captured only when the associated camera has detected motion within its field-of-view, thus reducing the storage requirements of the image archive platform. Since the Image Database is a generally-available network resource, it is thus possible to perform the Facial Processing on these stored images as well as on live camera video.
- the Facial Processors and Facial Database detect the presence of a person of interest in some live scene.
- the image archive it is possible to track the person's movements backward in time, thus re-constructing the person's movements through a facility. It is additionally possible, for example, to note whether the person-of-interest may have made contact with other people within the area being monitored.
- the system may then, upon command, derive a Facial Signature from that ‘new’ person's image, and add that new Facial Signature to the Facial Database.
- Historical analysis of the ‘new’ person's movements through the facility may then be performed, or the real-time location and movements of the ‘new’ person may be tracked.
- the Facial Database and the Image Archive may be two distinct platforms, both resident on the LAN or WAN, or where desired both functions may be resident on the same physical platform.
- the IP cameras include additional processing resources, and are thereby capable of performing the Facial Processing internally.
- the separate Facial Processors of the previous example are thereby eliminated. This approach allows improvement of the storage efficiency of the Image Database since images may, if desired, only be stored in the Image Archive if a face is recognized by one of the cameras, or if a particular predetermined face is detected by the Facial Database.
- Multicast protocols to support the one-camera-to-many-viewers nature of the surveillance system without duplicating network traffic.
- This Multicast network protocol lends itself well to the present invention.
- the Facial Processor is another ‘viewer’ on the network and no additional network traffic need be generated for it.
- Previous disclosures have described the use of Multicast protocol to convey the motion video, and Unicast protocols to convey the still-frame images to the image database.
- the still-frame images may also be conveyed over the network as Multicast data, since there is more than one recipient of the still images.
- the subject invention is directed to the overall integration of the Facial Recognition technology with the IP camera network.
- IP cameras produce a variety of real-time data streams.
- Motion video may be compressed into two simultaneous transport streams, such as a low-resolution QSIF stream and a higher-resolution SIF stream.
- SIF is normally 352 ⁇ 288 resolution
- QSIF is normally 176 ⁇ 144 resolution.
- Audio may be captured, digitized into a low-bit-rate stream for transport over the network.
- the still-frame images may be captured at a high resolution, say 704 ⁇ 480, and compressed into image files sufficiently small as to meet system requirements.
- these still-frame compressed image files may be conveyed by the network as a Multicast stream, or as a pair of Unicast streams.
- Monitor stations are configured to display the scenes captured by one or more of the networked video cameras.
- the monitor station may display one or multiple cameras.
- larger arrays display the low-resolution QSIF streams, while the single-camera array displays the selected camera's SIF output.
- the system also supports wireless monitor stations, typically used by guards or other law enforcement personnel who require mobility.
- An image server receives and stores still-frame images produced by the cameras for subsequent retrieval and analysis. These still-frame images are ordinarily produced only when the associated camera has detected motion within its field-of-view.
- the server may additionally be configured to store motion video streams upon detection of motion within its field-of-view.
- a facial database processor contains a stored database of the Facial Signatures and associated “mugshots” of some previously-defined persons.
- a facial processor detects faces within a selected camera's captured video, and subsequently derives unique Facial Signatures from the detected faces. Facial Signatures thus detected are forwarded to the Facial Database for correlation with a previously stored ‘library’ of facial mugshots, associated Facial Signatures, and database images in which the current Facial Signature was previously detected.
- an Image Database stores captured still images from the various IP cameras within the network. Each captured image is stored in some predetermined location within the server's file system. Each such image is represented by a unique Image ID number, maintained in a database file. Within the file, each record contains the Image ID number, as well as related data such as the date and time the image was taken, physical location where the image was taken, which camera captured the image, a fully-qualified URL describing where the image is located, and any Facial Signatures which were detected within the image.
- each unique Facial Signature file contains the Facial Signature data, the subject's name if known, age, weight, aliases if any, URL of a mugshot or separated facial image, URL of a biographical file if any, and image ID numbers of any Image Database records which contain the current Facial Signature.
- FIG. 1 (Prior Art) is a view of prior art facial recognition systems.
- FIG. 2 depicts the application of the basic Facial Recognition technology to a networked surveillance system.
- FIG. 3 is an expansion of the system of FIG. 2 showing the IP cameras with additional processing resources capable of performing the Facial Processing internally.
- FIG. 4 includes IP cameras for producing several motion MPEG video streams with different bandwidths, and additionally a high-resolution still frame JPEG image for storage in an image database.
- FIG. 5 depicts a typical structure for an Image Database and a Facial Signature Database.
- FIG. 6 depicts a typical screen layout of such a Monitor Station.
- FIG. 7 depicts the overall network.
- FIG. 8 depicts an expanded network for an airport system.
- FIG. 9 depicts typical apparatus used at curbside check-in for an airport system.
- FIG. 10 depicts a typical arrangement at a ticket counter of an airport system.
- FIG. 11 depicts the equipment at a typical entry point for checked baggage, such as at the ticket counter.
- FIG. 12 depicts the equipment at a typical security checkpoint used for passenger screening.
- FIG. 13 depicts the apparatus used at a typical boarding gate.
- FIG. 14 depicts an aircraft being loaded with checked baggage.
- FIG. 15 depicts apparatus installed on board a mass-transit vehicle, herein depicted as an aircraft.
- the subject invention provides both the method and apparatus for incorporating facial recognition technology into a comprehensive, multi-media surveillance system capable of: (1) identifying and looking for suspicious person; (2) providing access control; (3) attendance taking and verification; (4) identification and verification of friend or foe; (5) automated signaling upon verification of an issue; (6) management and distribution of the data; and (7) interconnectivity with other facial recognition databases and with other surveillance systems and equipment.
- the suspect finding and identification methodology includes:
- the access control function includes:
- the automated attendance function includes:
- the identification of friend or foe function includes:
- FIG. 1 depicts prior-art Facial Recognition systems.
- video camera 1 views a scene of interest
- processor 2 analyzes the video signals produced by the camera.
- the processor performs the steps of:
- FIG. 1 the basic function of the system can be enhanced as depicted in Prior Art # 2 .
- the processing function has been divided among several processors.
- One or more processors 3 perform the computationally intensive tasks of Facial Separation and Facial Signature generation, while processor 5 performs the less demanding task of database pattern matching.
- processors 3 perform the computationally intensive tasks of Facial Separation and Facial Signature generation, while processor 5 performs the less demanding task of database pattern matching.
- cameras and Facial Processors may be added incrementally to the system as needed, and it is unnecessary for each Facial Processor to contain or to access the entire ‘reference’ database.
- FIG. 2 depicts the application of the basic Facial Recognition technology to a networked surveillance system. Important aspects and features of the system and described in detail herein are the following:
- Camera 20 is an “IP camera”, as distinct from the conventional analog camera in the prior art.
- This IP camera perform additional processing steps to the captured video; specifically the captured video is digitized, compressed into a convenient compressed file format, and sent to a network protocol stack for subsequent conveyance over a local- or wide area network.
- Typical compression schemes include MPEG, JPEG, H.261 or H.263, wavelet, or a variety of proprietary compression schemes.
- a typical network topology is the popular Ethernet standard, IEEE 802.3, and may operate at speeds from 10 Mb/s to 100 Mb/s.
- Network protocols are typically TCP/IP, UDP/IP, and may be Unicast or Multicast as dictated by the system requirements.
- the cameras' compressed digital video is transported via Local Area Network (LAN) or Wide Area Network (WAN) 21 to a processor 22 which performs the steps of Facial Separation, Facial Signature Generation, and Facial Database Lookup.
- LAN Local Area Network
- WAN Wide Area Network
- FIG. 2 depicts in diagram “IP # 2 ”.
- a group of networked processors 25 perform the steps of Facial Separation and Facial Signature generation. This is distinct from the network topology of FIG. 1 , in which specific Facial Processors are dedicated to specific cameras.
- the Facial Processors 25 are treated as network resources, and are configured to process video from any networked camera as required. This improves the flexibility and economics of the system. For example, during periods when a particular area is not used, Facial Processors may be diverted from analysis of that particular camera to an area of higher traffic. Also, the workload of a failed Facial Processor may be diverted to a different processor.
- the Facial Database 24 may be treated as a general-purpose network resource, allowing a greater number of cameras 20 and Facial Processors 25 to perform Facial Signature lookups at any given time.
- the digital IP surveillance network is often part of a larger “network of networks”, thus allowing the Facial Database to be consulted by devices on a different network. This is useful in cases where different organizations may have compiled different Facial Databases. For example, an airport may maintain a database of the Facial Signatures of all current employees, as well as of past employees. A law enforcement organization may maintain a separate database of known offenders, and an Intelligence organization may maintain a current database of foreign nationals of interest. In the depicted networked environment, the Facial Processors 25 may consult several different Facial Databases, across the LAN or WAN.
- IP surveillance systems often maintain an archive 23 of stored video or images. Since this archive is generally available on the network, it is possible to use the system to search for faces in archived images, during event reconstruction.
- the IP surveillance network of FIG. 2 stores captured images or video in an Image Database 23 . Often, these images are captured only when the associated camera has detected motion within its field-of-view, thus reducing the storage requirements of the image archive platform. Since the Image Database 23 is a generally-available network resource, it is thus possible to perform the Facial Processing on these stored images as well as on live camera video.
- the Facial Processors 25 and Facial Database 24 detect the presence of a person of interest in some live scene. Using the image archive, it is possible to track the person's movements backward in time, thus re-constructing the person's movements through a facility. It is additionally possible, for example, to note whether the person-of-interest may have made contact with other people within the area being monitored. The system may then, upon command, derive a Facial Signature from that ‘new’ person's image, and add that new Facial Signature to the Facial Database. Historical analysis of the ‘new’ person's movements through the facility may then be performed, or the real-time location and movements of the ‘new’ person may be tracked.
- FIG. 2 depicts the Facial Database and the Image Archive as two distinct platforms, both resident on the LAN or WAN. It should be noted that these functions are essentially software, hence both functions may be resident on the same physical platform if system requirements so dictate.
- FIG. 3 depicts a further extension of the invention of FIG. 2 .
- the IP cameras 30 have been enhanced with additional processing resources, and are capable of performing the Facial Processing internally.
- the separate Facial Processors of the previous example are eliminated.
- this approach allows improvement of the storage efficiency of the Image Database 34 , since images may, if desired, only be stored in the Image Archive if a face is recognized by one of the cameras 30 , or if a particular predetermined face is detected by Facial Database 33 .
- the IP cameras 40 may produce multiple video streams as the system requirements may dictate.
- the IP cameras 40 may produce several motion MPEG video streams with different bandwidths (for different audiences), and may additionally produce a high-resolution still frame JPEG image for storage in an image database 45 .
- the system of FIG. 2 may utilize any of these video streams for facial recognition.
- the cameras 40 are IP-based, their motion video and still frame video streams are generally available upon demand throughout the network, and either type of video may be used to drive the Facial Recognition system.
- the still frame images have the advantage of greater resolution, but may be generated less frequently. Motion video sources may produce useful images more often, but at a reduced resolution. This reduced resolution decreases the accuracy of the Facial Recognition process.
- Multicast protocol is used to convey the motion video, and Unicast protocols to convey the still-frame images to the image database.
- the still-frame images may also be conveyed over the network as Multicast data, since there is more than one recipient of the still images.
- FIG. 4 depicts the overall integration of the Facial Recognition technology with the IP camera network.
- IP cameras 40 produce a variety of real-time data streams as shown.
- Motion video may be compressed into two simultaneous transport streams, such as a low-resolution QSIF stream and a higher-resolution SIF stream.
- SIF is normally 352 ⁇ 288 resolution
- QSIF is normally 176 ⁇ 144 resolution.
- Audio may be captured, digitized into a low-bit-rate stream for transport over the network.
- the still-frame images may be captured at a high resolution, say 704 ⁇ 480, and compressed into image files sufficiently small as to meet system requirements.
- These still-frame compressed image files may, as previously described, be conveyed by the network 47 as a Multicast stream, or as a pair of Unicast streams.
- FIG. 4 also depicts the remainder of the surveillance network.
- Monitor stations 41 and 44 are configured to display the scenes captured by one or more of the networked video cameras 40 .
- the monitor station may display one camera, or may display four cameras in a 2 ⁇ 2 array, nine cameras in a 3 ⁇ 3 array, or sixteen cameras in a 4 ⁇ 4 array.
- larger arrays such as 4 ⁇ 4 display the low-resolution QSIF streams, while the single-camera array displays the selected camera's SIF output.
- FIG. 4 additionally depicts a ‘wireless’ monitor station 43 , which receives selected video streams from the network via Wireless Access Point 42 . Due to the bandwidth constraints typical of wireless systems, a QSIF stream is normally displayed in the application. Such a wireless monitor station is typically used by guards or other law enforcement personnel who require mobility.
- FIG. 4 also depicts an image server 45 .
- This server receives and stores still-frame images produced by cameras 40 , for subsequent retrieval and analysis. These still-frame images are ordinarily produced only when the associated camera has detected motion within its field-of-view.
- Server 45 may additionally be configured to store motion video streams upon detection of motion within its field-of-view.
- a Facial Database 47 is depicted in FIG. 4 .
- this processor contains a stored database of the Facial Signatures and associated mugshots of some previously-defined persons.
- FIG. 4 depicts the networked Facial Processors 46 , which detect faces within selected camera's captured video, and which subsequently derive unique Facial Signatures from the detected faces. Facial Signatures thus detected are forwarded to the Facial Database 47 for correlation with a previously stored ‘library’ of facial mugshots, associated Facial Signatures, and database images in which the current Facial Signature was previously detected.
- FIG. 5 depicts a typical structure for an Image Database and a Facial Signature Database.
- the Image Database stores captured still images from the various IP cameras within the network. Each captured image is stored in some predetermined location within the server's file system. Each such image is represented by a unique Image ID number, maintained in a database file. Within the file, each record contains the Image ID number, as well as related data such as the date and time the image was taken, physical location where the image was taken, which camera captured the image, a fully-qualified URL describing where the image is located, and any facial Signatures which were detected within the image.
- each unique Facial Signature file contains the Facial Signature data, the subject's name if known, age, weight, aliases if any, URL of a mugs hot or separated facial image, URL of a biographical file if any, and image ID numbers of any Image Database records which contain the current Facial Signature.
- a Map Pane 61 contains a map of the facility under surveillance. This Map Pane may contain multiple maps, possibly representing different floors or buildings within a facility. Different maps may be displayed through common ‘point and click’ methods. Each map contains graphical icons representing the location and ID's of the various IP cameras available on the network.
- Video Pane 62 contains the current video of the selected camera or cameras. When viewing stored images from the Image Database, this Video Pane displays selected images from the database.
- a Control Pane 63 presents a variety of context-sensitive GUI User controls.
- the various IP cameras view scenes of interest, and one or more Monitor Stations display video from a selected group of cameras.
- Facial Processors locate faces in video from selected cameras, and derive Facial Signatures from the detected faces. These Facial Signatures are transmitted to a Facial Database, which searches through its stored Facial Signature library for a match.
- This information includes:
- the Image Database server may perform the following steps:
- the Facial Database detects a ‘hit’
- the location of the hit is depicted on map pane 61 of FIG. 6 .
- the appropriate map may be brought forward, if not already displayed, and the associated camera icon is highlighted, flashed, or otherwise made visually distinct.
- the subject person's current location within the facility is thus displayed.
- the associated camera icon is again highlighted, indicating the person's movements.
- Inquiries regarding the current location of individual personnel may be performed by the system.
- a previously-enrolled person is selected from the Facial Database, using the person's name, mugshot, employee ID, or other stored information. This selection may be made from a Graphical Interface on a networked Monitor Station.
- the Facial Database is then instructed to look for a ‘hit’ on that record.
- the Facial Database informs the Monitor Station of the match.
- the Monitor station may then highlight the camera icon of the associated camera, effectively locating the desired person on the map.
- the Monitor station may additionally bring that camera's video to the forefront, displaying a current image of the desired person.
- the desired person's movements may be compared against a known route, schedule, or database of approved/restricted locations.
- a security guard may have a predefined route to cover, which defines locations and times of his rounds.
- the Facial Database may be instructed to look through real-time images for a match with this person. If any such matches are found, they are compared with the times and locations defined by the guard's predefined schedule. If the guard successfully follows his usual rounds, the Facial Database can log this in a security log, including times and locations of the guards' route. If, however, the guard is not detected at the predefined location and/or time, this fact may be logged and, optionally, a system alarm may be generated to notify appropriate security personnel.
- hotel guests may be enrolled into the system at the time of registration.
- Hotel employees may likewise be enrolled into the system at the time of their employment.
- the system may be instructed to log the time and location of each successful facial detection, whether a database ‘hit’ occurs or not. If the facial detection does not match any person enrolled in the Facial Database, the system may generate an alarm, and indicate on a networked Monitor Station the location, and live video, where the face was detected. By way of example, common hotel burglars are thereby automatically detected and recorded by the system, and the system can be instructed to generate an alarm upon the next occurrence of this person.
- the system may determine what action to take based upon a pre-defined set of rules.
- the event is logged but no alarm is generated. If the guest is detected on the wrong floor, the event is logged and an alarm may or may not be generated based on a pre-defined qualifier. An employee may be detected, and an alarm may or may not be generated based on the employee's schedule or authorizations. For example, a cleaning lady on the correct floor at the correct time would not generate an alarm, but the same person on the wrong floor may generate an alarm.
- a previously unknown person may be ‘enrolled’ into the Facial Database, and a facility-wide search may be commenced.
- a lost child for example, may be enrolled into the system through the use of a photograph scanned into the Facial Database.
- all children entering some facility, such as an airport or theme park may be photographed and enrolled into the Facial Database.
- the Facial Database may then search all real-time camera video for a match with the enrolled child.
- a networked IP camera produces video which is subsequently determined to contain the lost child's face, one or more networked Monitor Stations alert security personnel of the event, and provide location and camera video of the lost child. Security personnel may then be dispatched to the location of the child.
- a person seen in a live image may be ‘tagged’ by an operator at a Monitor Station, whereupon the ‘tagged’ person's Facial Signature is added to the Facial Database.
- This is accomplished through the use of a GUI, wherein a specific still-frame image (or a frozen frame from a moving image) is displayed to the Monitor Station operator.
- the operator selects the desired face from the displayed image, through the use of a mouse or equivalent pointing device.
- the selected face is then separated from the image, the Facial Signature is derived, and the Facial Signature is added to the Facial Database.
- the operator is prompted to provide other pertinent information as appropriate to the application, such as a description of the observed event.
- the Facial Database may then be instructed to flag an operator whenever the ‘tagged’ person's image appears in any of the real-time images captured by the networked IP cameras. If the ‘tagged’ person's face is not observed by the Facial Database within some predefined time interval, then the Facial Database may be instructed to add the person's Facial Signature to a ‘watch list’ within the Facial Database. If the person's Facial Signature is subsequently detected by the Facial Database, then an alarm is generated, and selected Monitor Stations ‘pop’ the relevant information onto the Monitor Screen.
- the Facial Database may be instructed to search through the Image Database for all occurrences of the ‘tagged’ person's Facial Signature. This search may be made against the Image Database, or against the Facial Signature database, which keeps a record of all image filenames in which the selected Facial Signature occurs.
- the invention has applications in day-to-day law enforcement:
- the surveillance network may include the use of wireless, mobile Monitor Stations as well as the use of wireless IP cameras, all of which are part of the overall IP surveillance network.
- a patrol officers squad car may be equipped with both a wireless IP surveillance camera, as well as a wireless Monitor Station.
- the suspect's image may be captured by the car's wireless surveillance camera.
- the captured image may then be forwarded to a networked Facial Processor, which derives a Facial Signature from the suspect's image.
- This Facial Signature may be forwarded to the Facial Database, which looks for a match between the suspect's Facial Signature and any Facial Signatures which may have been previously recorded.
- Suspects may be quickly and accurately identified during the stop.
- a suspicious person's image is captured by a wireless IP surveillance camera, and the Facial Signature is generated as before.
- the Facial Signature is stored in the Facial Signature database, along with other information collected by the officer, such as location, time, type of activity observed, and so on. This information is then available to other officers via the Facial Signature database. If another officer encounters the person, the person's image may be again captured, and the ensuing Facial Signature match may alert the officers as to the previous suspicious activity.
- a person's behavioral pattern may be easily and systematically detected and recorded, such as a person who may be ‘casing’ a bank prior to a potential robbery.
- the surveillance network as supplemented with the Facial Recognition technology, finds usefulness in daily attendance applications:
- an IP camera may be trained at a classroom doorway, so as to capture facial images of attendees.
- the camera may be positioned to view the entire room.
- the images thus collected may be used to find faces, derive Facial Signatures, and compare a list of persons present to a class schedule database. This effectively automates the process of attendance taking.
- the system may thus record attendees, plus absentee or tardy students.
- the system may additionally correlate the real-time list of tardy or absent students against Facial Signatures of students detected in other areas of the school.
- the system may generate an alarm, and display the surveillance image of the student.
- the Monitor Station may additionally display relevant student information, such as name, current location, classroom where the student is scheduled to be, or prior attendance information.
- Panic Button a personal ‘Panic Button’, to be used by teachers or other personnel who may need to alert security personnel during an emergency.
- Facial Recognition technology to the networked surveillance system, also previously described, enhances the utility of the Panic Button.
- Personnel carry a radio transmitter with a button.
- the transmitter relays to a receiver that relays to the network the type of event (security request, medical request, fire request, etc.) and the individual who generated the event.
- the facial recognition system would then look for the last known location of that individual, and identify the event in that area—such as map indication, camera selection, and response personnel dispatch.
- the panic button transmitter may contain one or more pushbuttons labeled, for example, ‘FIRE’, ‘MEDIC’, “POLICE' and so on.
- an internal processor composes a message which encodes the identity of the person and the nature of the emergency (as derived from which button was pressed). This message is then transmitted to one or more networked receivers, and is displayed on one or more Monitor Stations. Security personnel may then be dispatched to the person's location as required.
- the location of the transmitter may only be determined to within the working radius of the receiver(s) that detected the transmission.
- receivers typically have a fairly broad coverage area, so as to minimize the total number of receivers required to completely cover the facility. Thus, localization of the person sending the alarm is of poor accuracy.
- Facial Recognition technology With the addition of Facial Recognition technology to the network, this problem is solved.
- the Facial Database looks up the person's Facial Signature, and proceeds to search all incoming video for a match. This localizes the person to within the field of view of one particular camera. The system additionally displays the current video from that camera.
- the Facial Database may be instructed to search the Image Database for the person's image. Such a search would start at the most recently stored images, preferably starting with previously known locations, if any, where the person was scheduled to have been. When a match is detected, the Monitor Station may be instructed to display the most recent image containing the person's image.
- Certain types of security alarm events may require the dispatch of specific types of personnel:
- a fire alarm might require the immediate dispatch of firefighters, while a medical alarm might require the immediate dispatch of a nurse or doctor.
- a security violation at an entrance door may require the dispatch of a security guard.
- the Facial Database is instructed to search all incoming video for a Facial Signature match with one of a group of pre-enrolled firefighters.
- a Facial Database successfully detects one or more of these firefighters, their current location is indicated on the Monitor Station. This indication may be via graphical icons on the facility map, or by displaying the camera(s) which contain their video. In either case, the available firefighters are located, and the nearest ones can be dispatched to the scene of the fire.
- Previous examples have mostly involved the use of a pre-defined database of Facial Signatures.
- Other applications of the system may involve the use of a Facial Database that is collected over a period of time.
- Databases of individuals can be built-up automatically. Link of the surveillance system, with other systems such as ATMs, ticketing systems, and the like can be made. As an individual does a transaction his facial signature is logged. If another transaction is attempted but a different facial signature is involved, and alarm is generated.
- airline tickets are used under a specific name and a facial signature and an image are collected. If the same name is used again, but a different facial signature is seen, an alarm event is generated. The use of the previously captured image can be utilized for operator intervention to determine what has happened.
- an ATM card or Credit Card is used.
- the system captures a facial signature for that specific card.
- An image of the user is captured and stored as well. If that card is used but a different facial signature is seen, and alarm event is generated. The use of the previously captured image can be utilized for operator intervention to determine what has happened.
- prescription drugs are purchased under a specific name and a facial signature and an image are collected. If the same name is used again, but a different facial signature is seen, and alarm event is generated. The use of the previously captured image can be utilized for operator intervention to determine what has happened.
- the Facial Database alerts other linked systems to perform a search for any transaction involving that ATM or credit card.
- the Facial Database alerts other security networks to search any available camera video for that person's Facial Signature.
- the person's Facial Signature may be forwarded to other banks in the area, which may be instructed to search for any ATM transaction, or any camera video at all which contains the selected Facial Signature.
- An area can be monitored for repeated (suspicious) access by specific but unknown individuals. If the repeated access is over a selected threshold point, an alarm can be indicated. Images can be stored with attached facial signatures. A search of that facial signature would then bring up all images of that individual.
- a bank can have a facial database of all current customers and bank personnel. If an unknown individual appears in the recognition system several times without becoming an employee or customer, this could create an alarm condition. A search by facial signature can go back in the database and allow investigation of what that individual was doing. If it is a known benign individual, such as the postman making mail delivery is seen, a GUI can allow “tagging” that individual from unknown to known. This would prevent generation of future alarms when that particular individual is recognized.
- Networked security surveillance systems such as described may use Facial Recognition methods to spot developments or trends that may be of interest. For example, a bank's surveillance network may automatically detect and enroll all faces captured by its network of security cameras. The Facial Database may then be searched for trends, such as a new face that appears on the scene and which becomes persistent or periodic. The Facial Database may then alert security personnel to these detected patterns, via a networked Monitor Station.
- Facial Recognition methods to spot developments or trends that may be of interest. For example, a bank's surveillance network may automatically detect and enroll all faces captured by its network of security cameras. The Facial Database may then be searched for trends, such as a new face that appears on the scene and which becomes persistent or periodic. The Facial Database may then alert security personnel to these detected patterns, via a networked Monitor Station.
- Facial Database which defines these regularly-detected Facial Signatures as ‘approved’, along with appropriate identifying information.
- Some of these cases might be people reconnoitering the premises in preparation for a crime.
- security personnel may be notified via a networked Monitoring Station, and personnel may be directed to intercept the person immediately, or upon the next detection of the person.
- the Image Database may be searched for any occurrences of that person's Facial Signature, as part of the event analysis.
- a networked camera captures a person at a door camera, the recognizer identifies the individual, a database lookup occurs to see if that individual is authorized for access at that time and place, access is allowed, a signal is sent to an electric door strike or other control device to allow access.
- doorways are each equipped with a networked IP surveillance camera, positioned to capture the face of the person seeking entry.
- the Facial Database searches for a match between the detected person's Facial Signature, and a Facial Signature in the Facial Database. If the detected person's Facial Signature is found in the Facial Database, on a list of ‘approved’ persons, the Facial Database commands the electric door ‘strike’ to open and allow the person entry to (or exit from) the facility.
- the networked surveillance system enhanced with Facial Recognition capabilities, may be configured to automate detection of such violations.
- a database of affected personnel such as students or minors is created. This can be done at schools, or by means of photos on driver's licenses, for example. Cameras patrolling common street areas are deployed with facial recognition. If such people are detected in the street after curfew time, an alarm is generated and response personnel dispatched.
- the networked Facial Database may be loaded with still-frame images and Facial Signatures of underage persons, perhaps from a Facial Database generated by the public schools, or from a Juvenile court, or the like.
- Facial Signature of a captured face matches a face in the Facial Database, police or other appropriate personnel may be dispatched to the location.
- the system may also be interfaced to a point of sale system, such as a gasoline pump.
- a point of sale system such as a gasoline pump.
- An image of the person activating the pump is collected. If that individual leaves the store without paying, the facial signature and image of that individual is added to the “drive-off” list. If that individual returns to that store, the pump will be locked out and personnel can be notified of a former drive-off suspect.
- drive off facial signatures can be forwarded to other stations to prevent that person from accessing pumps at other locations, and assist in apprehending that person.
- Retail establishments can collect images in conjunction with retail transactions such as use of membership cards, checks or credit cards.
- a facial signature of the associated image is generated. If the transaction “goes bad” the facial signature can be so noted and shared with other retail establishments. This can be within one company, it can be a cooperative service with many members, or it can be an extension of check and credit card verification services. This prevents multiple use of stolen or forged checks, credit cards, and the like.
- FIGS. 7 through 15 depict a comprehensive integration of the networked video surveillance system with Facial Recognition technology and with commonplace or legacy airport security measures.
- airport security measures include metal detectors, baggage X-ray scanners, scales, and related devices.
- An integrated network of said devices improves security throughout the air travel system.
- FIG. 7 depicts the overall network.
- Various airports 70 each contain a Local Area Network (LAN) to interconnect their various security equipment.
- Each airport is equipped, for example, with Networked Security Cameras at the curbside check-in point(s) 75 , at the ticket counter(s) 76 , the security screening point(s) 77 , the various gate counters 78 , and at the entrance to each jetway 79 .
- the airport facility is equipped with a group of Networked Surveillance Cameras, providing surveillance coverage of other areas of interest, including concourses, restaurants, baggage handling areas, aircraft loading areas on the tarmac, and so on.
- These Airport LANs are all interconnected via a national Inter-Airport WAN 71 , permitting efficient dissemination and sharing of security data between airports 70 and with en-route aircraft 74 via ground station/satellite communications link 73 .
- FIG. 8 depicts the airport network in greater detail.
- Networked Surveillance Cameras 80 A through 80 E are stationed at the various security checkpoints as indicated, including curbside check-in, ticket counters, security checkpoints, gate counters, boarding gates, and so on.
- the Airport Security LAN contains Networked Monitoring Stations 85 , Networked Facial Processors 86 , Networked Image Database 87 , and a Networked Facial Database 88 .
- the Airport LAN has a connection to the National Airport Security WAN.
- Additional Networked Surveillance Cameras 80 are installed in various areas of interest within the airport as previously discussed.
- the security checkpoints contain other Networked devices as appropriate to the function of the checkpoint.
- scanner 81 A is used to scan a departing passenger's photo ID and ticket, and thereupon store such captured information into the airport's networked Image Database.
- a scale 82 A and explosive sensor 83 are used in screening passengers, again storing such captured information into the networked airport Image Database.
- FIG. 9 depicts typical apparatus used at curbside check-in.
- Passengers 91 A and 91 B arrive at curbside for check-in.
- Networked Surveillance Cameras 90 A and 90 B capture their image, for subsequent Facial Analysis and enrollment into the airports Networked Facial Database.
- Their baggage, 92 A and 92 B respectively is additionally photographed by cameras 90 A and 90 B, and is weighed by a networked scale 93 , and the resulting weight reading is stored in the airport's networked Image Database along with the passenger's captured Facial Signature.
- the passenger's Photo ID and tickets are scanned with networked scanner 95 , and the resulting images are additionally stored in the airport's networked Image Database.
- FIG. 10 depicts a typical arrangement at a ticket counter.
- Passenger 103 arrives at the Ticket Counter for ticketing and baggage check.
- Networked Surveillance Camera 100 A captures the person's image, for subsequent Facial Processing and Image storage.
- the passenger's baggage is weighed by networked scale 101 , and the baggage is imaged by networked surveillance camera 100 B.
- the baggage's image and weight are transferred via hub 104 to the Airport LAN, and subsequently to the networked Facial Database, and are appended to the passenger's file record in the Facial Database.
- the passenger's ticket and photo ID are scanned by networked scanner 102 , and the resulting images are transferred, via the airport LAN, to the networked Image Database.
- Other ticket-counter scanners such as an explosives sensor, an X-Ray scanner, or a scale 105 for weighing the passenger, likewise produce data which are appended to the passenger's record in the Facial Database.
- the person's Facial Signature (as derived from camera 100 A′s captured image) may be compared with the Facial Signature derived from the person's photo ID scan, for identity verification of the passenger.
- data describing the passenger's baggage has been captured by the system and stored in the passenger's Facial Database file, for subsequent bag and identity matching.
- FIG. 11 depicts the equipment at a typical entry point for checked baggage, such as at the ticket counter.
- a networked image scanner captures the passenger's photo ID, which may be a driver's license or a passport.
- Camera 111 A captures an image of the passenger and baggage at that time, and the ensuing Facial Signature may be confirmed against the Facial Signature derived from the passenger's photo ID.
- the passenger's checked baggage is scanned by X-ray scanner 113 , and the X-ray imagery thus produced is captured by Networked Surveillance Encoder 112 , and subsequently appended to the Passenger's record in the Facial Database.
- An additional Networked Surveillance camera 111 B images the passenger's baggage as it leaves the X-ray scanner, and the resulting image is appended to the networked Image Database.
- a networked explosives sensor 115 likewise produces data descriptive of the baggage, and is likewise appended to the networked Image Database.
- FIG. 12 depicts the equipment at a typical security checkpoint used for passenger screening.
- Passengers arrive at the security checkpoint and deposit their carry-on baggage on the conveyor belt of X-ray scanner 123 .
- they are photographed by networked surveillance camera 121 A.
- the image is stored in the network's Image Database, and a networked Facial Processor derives a Facial Signature for the passenger.
- This data is appended to the existing record in the Facial Database representing that passenger.
- the passenger's photo ID and ticket are scanned into networked scanner 120 A, and this data is appended to the passenger's file as well.
- a further networked surveillance camera may be used, if needed, at an inspection table, near the passenger metal detector, to capture an image of any personal items from the person's pockets or purse, or other personal luggage, during such an inspection. This image, as well, is appended to the passenger's record in the database.
- data from a networked explosives scanner, and scanned images of the passenger's luggage tag may be added to the passenger's record in the database.
- networked surveillance camera 121 B captures an image of the passenger's carry-on baggage, and appends it to the passenger's record in the Facial Database.
- networked surveillance encoder 124 captures the scanned image from x-ray scanner 123 , and again appends it to the passenger's file.
- Networked surveillance camera 121 C captures an image of the carry-on baggage as it leaves the X-ray scanner 123 , and may optionally be positioned to capture an image of both the carry-on baggage as well as the passenger as they retrieve their carry-on baggage from the conveyor. Again, these captured images are appended to the passenger's file.
- FIG. 13 depicts the apparatus used at a typical boarding gate.
- the passenger's ticket and photo ID are scanned, and added to the passenger's database entry. Additionally, the passenger is photographed by networked surveillance camera 133 .
- a facial signature from the passenger's photo ID, and a Facial Signature derived from camera 133 's captured image, may be compared to verify the passenger's identity. Either or both of these Facial Signatures may additionally be compared with similar entries previously added to the passenger's database record, again verifying the passenger's identity.
- FIG. 14 depicts an aircraft 140 being loaded with checked baggage.
- a networked surveillance camera 141 captures an image of the bag.
- a handheld barcode scanner 144 captures the data from the barcoded baggage tag.
- the bag's image is transferred, via the facility's security LAN, to the Image Database for storage.
- the baggage barcode is stored in the passenger's file. This allows subsequent matching of baggage, as loaded onto the aircraft, with baggage that had been previously matched to a known passenger.
Abstract
Embodiments provide a surveillance system having at least one camera adapted to produce an IP signal, the at least one camera having an image collection device configured for collecting image data, the at least one camera having at least one facial processor configured to execute with digital format image data at least one facial recognition algorithm, execution of the at least one facial recognition algorithm with the digital format image data detecting faces when present in the digital format image data, execution of the at least one
facial recognition algorithm providing for each detected face at least one set of unique facial image data.
Description
- This application is a Continuation of application Ser. No. 10/719,792, filed on Nov. 21, 2002, titled “Method for Incorporating Facial Recognition Technology in a Multimedia Surveillance System”, the entire contents of which are incorporated herein by reference.
- 1. Field of the Invention
- The invention generally relates to use of facial recognition technology as used in surveillance and access systems and is specifically directed to incorporation of such technology in an IP compatible, networked, comprehensive multimedia surveillance system.
- 2. Discussion of the Prior Art
- My earlier patents and applications have covered various aspects of the networked multimedia surveillance system in detail. My following earlier patents and pending applications are incorporated herein by reference:
- Ser. No. 10/192,870 Filing Date: Jul. 10, 2002
- Ser. No. 08/738,487 Filing Date: Oct. 28, 1996
U.S. Pat. No. 5,798,458 Issue Date: Aug. 25, 1998 - Ser. No. 08/745,536 Filing Date: Nov. 12, 1996
U.S. Pat. No. 6,009,356 Issue Date: Dec. 28, 1999 - Ser. No. 08/815,026 Filing Date: Mar. 14, 1997
U.S. Pat. No. 5,943,140 Issue Date: Aug. 24, 1999 - Ser. No. 09/143,232 Filing Date: Aug. 28, 1998
- Ser. No. 09/257,448 Filing Date: Feb. 25, 1999
- Ser. No. 09/257,720 Filing Date: Feb. 25, 1999
U.S. Pat. No. 6,392,692 Issue Date: May 21, 2002 - Ser. No. 09/257,765 Filing Date: Feb. 25, 1999
U.S. Pat. No. 6,366,311 Issue Date: Apr. 2, 2002 - Ser. No. 09/257,767 Filing Date: Feb. 25, 1999
U.S. Pat. No. 6,246,320 Issue Date: Jun. 12, 2001 - Ser. No. 09/257/769 Filing Date: Feb. 25, 1999
- Ser. No. 09/257,802 Filing Date: Feb. 25, 1999
U.S. Pat. No. 6,253,064 Issue Date: Jun. 26, 2001 - Ser. No. 09/593,901 Filing Date Jun. 14, 2000
- Ser. No. 09/594,041 Filing Date: Jun. 14, 2000
- Ser. No. 09/687,713 Filing Date: Oct. 13, 2000
- Ser. No. 09/966,130 Filing Date: Sep. 21, 2001
Title: Multimedia Network Appliances for Security and Surveillance application
Ser. No. 09/974,337 Filing Date: Oct. 10, 2001 - Ser. No. 09/715,783 Filing Date: Nov. 17, 2000
- Ser. No. 09/716,141 Filing Date: Nov. 17, 2000
- Ser. No. 09/725,368 Filing Date: Nov. 29, 2000
- Ser. No. 09/853,274 Filing Date: May 11, 2001
- Ser. No. 09/854,033 Filing Date: May 11, 2001
- Ser. No. 09/866,984 Filing Date: May 29, 2001
- Ser. No. 09/960,126 Filing Date: Sep. 21, 2001
- Ser. No. 10/134,413 Filing Date: Apr. 29, 2002
- Several companies have developed computer algorithms that are capable of producing a “digital signature” from video images of people's faces. These signatures are much like a fingerprint: they are unique to individuals; they are relatively small so they are efficient; and, they may be used in databases to look up the identity and other data about the person.
- While other types of biometrics, such as iris scanning, are at best or even more accurate than facial recognition (which has a relatively low error rate; just under 1 percent), facial recognition will probably be accepted more widely because it is not intrusive. Further, it does not require that the user push, insert or click on anything. Companies often do not need to install anything beyond the new software because most already have cameras in place and pictures of employees on file—making it less expensive than iris reading setups. In addition, the relatively small size of the database for a facial profile makes it an attractive technology.
- One example of a currently available facial recognition software is the Visionics' FaceIt system. The FaceIt software measures a face according to its peaks and valleys—such as the tip of the nose, the depth of the eye sockets—which are known as nodal points. A typical human face has 80 nodal points and precise recognition can be achieved with as few as 14 to 22 utilizing the FaceIt system. Specifically, the FaceIt system concentrates on the inner region of the face, which runs from temple to temple and just over the lip, called the ‘golden triangle.’ This is the most stable because even if facial hair such as a beard is altered, or if the subject changes or adds glasses, changes in weight or ages substantially the ‘golden triangle’ region tends to not be affected, while places such as under chin would be substantially altered. FaceIt plots the relative positions of these points and comes up with a long string of numbers, called a faceprint.
- Visage Technology of Littleton, Mass., has a slightly different model. Its software compares faces to 128 archetypes it has on record. Faces are then assigned numbers according to how they are similar or different from these models. The Visage Technology has been utilized to date in the identification of criminals, for access control, for transaction security and for identity fraud prevention.
- Most recently, government and aviation officials are poised to begin using facial recognition systems to scan airport terminals for suspected “terrorists. Recently, Visionics has teamed up with a domestic airline to demonstrate a conceptual boarding system that will use FaceIt to facilitate the rapid boarding of the airline's frequent flyers.
- In the past, law enforcement officials often have no more than a facial image to link a suspect to a particular crime or previous event. Up to now, database searches were limited to textual entries (i.e., name, social security number, birth date, etc.), leaving room for error and oversight. By conducting searches against facial images, the facial recognition technology permits rapid review of information and quickly generated results, with the ability to check literally millions of records for possible matches, and then automatically and reliably verifying the identity of a suspect.
- The facial recognition technology has several advantages over other biometric systems. For example, with facial recognition technology a person can be identified at a distance or in a crowd. The technology has the capability of capturing a face in the field of view, extract the face from the background data and compare it against a database.
- The system permits the creation of watch lists or the like. This could include, for example, known shoplifters, terrorists or criminals, as well as frequent customers, VIP's, expected visitors or individuals generally classified as friends or foes. The system can be used at airports, casinos, public buildings, schools, subways, colleges, factories, business facilities, housing complexes, residences and the like.
- The system also is useful in transaction modes. Customers are used to being verified or being recognized by their face at retail locations by providing merchants with a driver's license or other form of photo ID. In sharp contrast to today's widely used signature verification process, which is highly unreliable and cannot be accurately determined by unskilled and untrained clerks, face recognition makes verification reliable, automatic and fast. In banking, facial recognition technology can adapt to already installed ATM cameras for recognizing and verifying customer identities so the financial transaction can be quickly and effortlessly conducted. Such technology can replace reliance on alphanumeric PINs to identify and authenticate a user.
- Face recognition is the only biometric that can be used in two modalities—logon and continuous monitoring. An example of logon modality is use as a perimeter defense mechanism, where an authorized individual gains entry to a network or session after a one-time logon process. This is the typical mode for all biometric systems. In addition, face recognition supports a continuous monitoring mode where persons are continuously authenticated for ensuring that at all times the individual in front of the computer or handheld device continues to be the same authorized person who logged in.
- Currently available technology focuses on the following aspects of facial recognition:
- Detection—When the system is attached to a video surveillance system, the recognition software searches the field of view of a video camera for faces. If there is a face in the view, it is detected within a fraction of a second. A multi-scale algorithm is used to search for faces in low resolution. The system switches to a high-resolution search only after a head-like shape is detected.
- Alignment—Once a face is detected, the system determines the head's position, size and pose to assure that the face is appropriately turned toward the camera for the system to register it.
- Normalization—The image of the head is scaled and rotated so that it can be registered and mapped into an appropriate size and pose. Normalization is performed regardless of the head's location and distance from the camera.
- Representation—The system translates the facial data into a unique code. This coding process allows for easier comparison of the newly acquired facial data to stored facial data.
- Matching—The newly acquired facial data is compared to the stored data and linked to at least one stored facial representation.
- The heart of current facial recognition systems is the algorithm. This is the mathematical technique the system uses to encode faces. The system maps the face and creates a faceprint, a unique numerical code for that face. Once the system has stored a faceprint, it can compare it to the thousands or millions of faceprints stored in a database. In the FaceIt system, each faceprint requires an 84-byte file. The FaceIt system can match multiple faceprints at a rate of up to 60 million per minute. As comparisons are made, the system assigns a value to the comparison using a scale of 1 to 10. If a score is above a predetermined threshold, a match is declared. The operator then views the two photos that have been declared a match to be certain that the computer is accurate.
- As the facial recognition technology develops, expanding uses are desirable. A comprehensive, system approach incorporating this technology with other legacy, digital and IP system architectures is needed. A comprehensive, coordinated approach utilizing this technology with known surveillance techniques and with system collection, distribution and management techniques will be required to maximize the value of this and other biometric recognition technologies.
- The subject invention is directed to the integration of facial recognition capability into a multimedia security system with IP compatibility for enhancing the collection, distribution and management of recognition data by utilizing the system's cameras, databases, monitor stations, and notification systems.
- In its simplest configuration, a camera views a scene of interest, and a processor analyzes the video signals produced by the camera. The processor performs the steps of:
-
- Facial Separation, e.g., locating human faces within the viewed scene,
- Facial Signature generation, e.g., deriving a unique identifying descriptor for the detected faces,
- Database Creation, adding said descriptors and separated facial image to a comparison database,
- Database Lookup, matching the captured descriptors with previously-captured faces or images containing faces or other relevant data, and
- Generating alarms as appropriate.
- The basic function of the system can be enhanced by dividing the processing function processors. One or more processors perform the computationally intensive tasks of Facial Separation and Facial Signature generation, while yet another processor performs the less demanding task of database pattern matching. This yields improved system economies and flexibility. Cameras and Facial Processors may be added incrementally to the system as needed, and as is unnecessary for each Facial Processor to contain or to access the entire ‘reference’ database.
- In the subject invention, the basic facial recognition technology is incorporated into a networked surveillance system. In the preferred embodiment of the system, at least one camera, ideally an IP camera, is provided. This IP camera performs additional processing steps to the captured video; specifically the captured video is digitized, compressed into a convenient compressed file format, and sent to a network protocol stack for subsequent conveyance over a local or wide area network. Typical compression schemes include MPEG, JPEG, 11.261 or H.263, wavelet, or a variety of proprietary compression schemes. A typical network topology is the popular Ethernet standard, IEEE 802.3, and may operate at speeds from 10 Mb/s to 100 Mb/s. Network protocols are typically TCP/IP, UDP/IP, and may be Unicast or Multicast as dictated by the system requirements.
- The compressed digital video is transported via Local Area Network (LAN) or Wide Area Network (WAN) to a processor which performs the steps of Facial Separation, Facial Signature Generation, and Facial Database Lookup.
- The utility of the system may be enhanced by the increased use of the networking techniques of the subject invention. In this enhancement, a group of networked processors perform the steps of Facial Separation and Facial Signature generation. The Facial Processors function as network resources, and are configured to process video from any networked camera, as required. This improves the flexibility and economics of the system. For example, during periods when a particular area is not used, Facial Processors may be diverted from analysis of that particular camera to an area of higher traffic. Also, the workload of a failed Facial Processor may be diverted to a different processor.
- Other benefits arise from this configuration. For example, the Facial Database may be treated as a general-purpose network resource, allowing a greater number of cameras and Facial Processors to perform Facial Signature lookups at any given time. Moreover, the digital IP surveillance network is often part of a larger “network of networks”, thus allowing the Facial. Database to be consulted by devices on a different network. This is useful in cases where different organizations may have compiled different Facial Databases. For example, an airport may maintain a database of the Facial Signatures of all current employees, as well as of past employees. A law enforcement organization may maintain a separate database of known offenders, and an Intelligence organization may maintain a current database of foreign nationals of interest. In the depicted networked environment, the Facial Processors may consult several different Facial Databases, across the LAN or WAN.
- An additional benefit arises from the fact that IP surveillance systems often maintain an archive of stored video or images. Since this archive is generally available on the network, it is possible to use the system to search for faces in archived images, during event reconstruction. In the preferred embodiment the IP surveillance network stores captured images or video in an Image Database. Often, these images are captured only when the associated camera has detected motion within its field-of-view, thus reducing the storage requirements of the image archive platform. Since the Image Database is a generally-available network resource, it is thus possible to perform the Facial Processing on these stored images as well as on live camera video.
- For example, the Facial Processors and Facial Database detect the presence of a person of interest in some live scene. Using the image archive, it is possible to track the person's movements backward in time, thus re-constructing the person's movements through a facility. It is additionally possible, for example, to note whether the person-of-interest may have made contact with other people within the area being monitored. The system may then, upon command, derive a Facial Signature from that ‘new’ person's image, and add that new Facial Signature to the Facial Database. Historical analysis of the ‘new’ person's movements through the facility may then be performed, or the real-time location and movements of the ‘new’ person may be tracked.
- The Facial Database and the Image Archive may be two distinct platforms, both resident on the LAN or WAN, or where desired both functions may be resident on the same physical platform.
- In a further enhancement of the invention, the IP cameras include additional processing resources, and are thereby capable of performing the Facial Processing internally. The separate Facial Processors of the previous example are thereby eliminated. This approach allows improvement of the storage efficiency of the Image Database since images may, if desired, only be stored in the Image Archive if a face is recognized by one of the cameras, or if a particular predetermined face is detected by the Facial Database.
- My previous applications and patents as listed above and as incorporated by reference herein describe a surveillance system wherein the IP cameras may produce multiple video streams as the system requirements may dictate. For example, the IP cameras may produce several motion MPEG video streams with different bandwidths (for different audiences), and may additionally produce a high-resolution still frame JPEG image for storage in an image database. The system may utilize any of these video streams for facial recognition. Since the cameras are IP-based, their motion video and still frame video streams are generally available upon demand throughout the network, and either type of video may be used to drive the Facial Recognition system. The still frame images have the advantage of greater resolution, but may be generated less frequently. Motion video sources may produce useful images more often, but at a reduced resolution. This reduced resolution decreases the accuracy of the Facial Recognition process.
- Prior disclosures have additionally described the use of Multicast protocols to support the one-camera-to-many-viewers nature of the surveillance system without duplicating network traffic. This Multicast network protocol lends itself well to the present invention. Specifically, the Facial Processor is another ‘viewer’ on the network and no additional network traffic need be generated for it. Previous disclosures have described the use of Multicast protocol to convey the motion video, and Unicast protocols to convey the still-frame images to the image database. In the present invention, the still-frame images may also be conveyed over the network as Multicast data, since there is more than one recipient of the still images.
- The subject invention is directed to the overall integration of the Facial Recognition technology with the IP camera network. IP cameras produce a variety of real-time data streams. Motion video may be compressed into two simultaneous transport streams, such as a low-resolution QSIF stream and a higher-resolution SIF stream. (SIF is normally 352×288 resolution, and QSIF is normally 176×144 resolution.)
- Audio may be captured, digitized into a low-bit-rate stream for transport over the network. In addition, the still-frame images may be captured at a high resolution, say 704×480, and compressed into image files sufficiently small as to meet system requirements. As previously described, these still-frame compressed image files may be conveyed by the network as a Multicast stream, or as a pair of Unicast streams.
- Monitor stations are configured to display the scenes captured by one or more of the networked video cameras. The monitor station may display one or multiple cameras. To conserve system bandwidth and the monitor station processing capacity, larger arrays display the low-resolution QSIF streams, while the single-camera array displays the selected camera's SIF output. The system also supports wireless monitor stations, typically used by guards or other law enforcement personnel who require mobility.
- An image server receives and stores still-frame images produced by the cameras for subsequent retrieval and analysis. These still-frame images are ordinarily produced only when the associated camera has detected motion within its field-of-view. The server may additionally be configured to store motion video streams upon detection of motion within its field-of-view. A facial database processor contains a stored database of the Facial Signatures and associated “mugshots” of some previously-defined persons. A facial processor detects faces within a selected camera's captured video, and subsequently derives unique Facial Signatures from the detected faces. Facial Signatures thus detected are forwarded to the Facial Database for correlation with a previously stored ‘library’ of facial mugshots, associated Facial Signatures, and database images in which the current Facial Signature was previously detected.
- In one configuration of the invention an Image Database stores captured still images from the various IP cameras within the network. Each captured image is stored in some predetermined location within the server's file system. Each such image is represented by a unique Image ID number, maintained in a database file. Within the file, each record contains the Image ID number, as well as related data such as the date and time the image was taken, physical location where the image was taken, which camera captured the image, a fully-qualified URL describing where the image is located, and any Facial Signatures which were detected within the image.
- In a typical structure for the Facial Signature Database, each unique Facial Signature file contains the Facial Signature data, the subject's name if known, age, weight, aliases if any, URL of a mugshot or separated facial image, URL of a biographical file if any, and image ID numbers of any Image Database records which contain the current Facial Signature.
- There are several primary objectives of the invention, directed to the following activities: (1) identifying and looking for suspicious person; (2) providing access control; (3) attendance taking and verification; (4) identification and verification of friend or foe; (5) automated signaling upon verification of an issue; (6) management and distribution of the data; and (7) interconnectivity with other facial recognition databases and with other surveillance systems and equipment.
- It is, therefore, an object and feature of the invention to integrate facial recognition technology with other surveillance technology for defining an enhanced multi-media surveillance capability.
- It is also an object and feature of the subject invention to provide improved facial recognition capability by utilizing high resolution digital camera technology to capture the image.
- It is another object and feature of the subject invention to provide interconnectivity between facial recognition systems and other surveillance systems.
- It is an object and feature of the subject invention to provide an IP network capability for transmitting facial recognition data using IP protocol.
- It is a further object and feature of the subject invention to provide off network connectivity of the facial recognition database to other database system including national archives and the like.
- It is another object of the invention to provide management and distribution of facial recognition data.
- Other objects and features of the invention will be readily apparent from the accompanying drawings and detailed description of the preferred embodiment.
-
FIG. 1 (Prior Art) is a view of prior art facial recognition systems. -
FIG. 2 depicts the application of the basic Facial Recognition technology to a networked surveillance system. -
FIG. 3 is an expansion of the system ofFIG. 2 showing the IP cameras with additional processing resources capable of performing the Facial Processing internally. -
FIG. 4 includes IP cameras for producing several motion MPEG video streams with different bandwidths, and additionally a high-resolution still frame JPEG image for storage in an image database. -
FIG. 5 depicts a typical structure for an Image Database and a Facial Signature Database. -
FIG. 6 depicts a typical screen layout of such a Monitor Station. -
FIG. 7 depicts the overall network. -
FIG. 8 depicts an expanded network for an airport system. -
FIG. 9 depicts typical apparatus used at curbside check-in for an airport system. -
FIG. 10 depicts a typical arrangement at a ticket counter of an airport system. -
FIG. 11 depicts the equipment at a typical entry point for checked baggage, such as at the ticket counter. -
FIG. 12 depicts the equipment at a typical security checkpoint used for passenger screening. -
FIG. 13 depicts the apparatus used at a typical boarding gate. -
FIG. 14 depicts an aircraft being loaded with checked baggage. -
FIG. 15 depicts apparatus installed on board a mass-transit vehicle, herein depicted as an aircraft. - The subject invention provides both the method and apparatus for incorporating facial recognition technology into a comprehensive, multi-media surveillance system capable of: (1) identifying and looking for suspicious person; (2) providing access control; (3) attendance taking and verification; (4) identification and verification of friend or foe; (5) automated signaling upon verification of an issue; (6) management and distribution of the data; and (7) interconnectivity with other facial recognition databases and with other surveillance systems and equipment.
- The suspect finding and identification methodology includes:
-
- Running the Facial Recognition on the camera data;
- Running the Facial Recognition Algorithms on the Archival Database;
- Generating and storing a Facial Signature for each person that was in the field of view for future analysis;
- Automatic indexing into the Database based on signature;
- When a Suspect match has occurred, dispatch an event alarm to a wire monitor station;
- When a Suspect Match has occurred, dispatch an event alarm to a wireless monitor station, such as in a police car or a unit carried by an officer; and
- When a Suspect Match has occurred, dispatch and event alarm by telephone, cellular telephone, by pager, by digital pager, by e-mail such as through a security notification system.
- The access control function includes:
-
- Integrating the Facial Recognition with an access control database. Store the signature and the access allowed/denied;
- Notification on the access denied utilizing the notification system; and
- Access/No Access can be shown on monitors station(s).
- The automated attendance function includes:
-
- Example—an employee reports to work. The camera detects her/him entering and the employee is logged in. The camera (or another camera) detects her/him leaving and the employee is logged out. This can be automatic, or can be in conjunction with pushing an in/out interface device.
- Example—in a school a student enters a room through a door that is surveilled by a camera. As he/she enters, the student is identified and counted in attendance. Time can be part of the equation. If the student is late to class by a few minutes, the student will be counted tardy and the amount of time late recorded. If the student comes very late, attendance will not be recorded.
- A camera covering the entire room can also be utilized. The camera will have a view of all seats in the classroom. A “video roll call” of the classroom will be taken in a manner similar to the above.
- The identification of friend or foe function includes:
-
- Faceprints of known individuals, such as employees or contract personnel, would be placed in a database.
- Areas that are accessible by each person could also be put in the database.
- If an UNKNOWN person is identified in a field of view, and alarm condition is generated.
- The video is automatically switched at a monitor station and the unknown individual is flagged, such as by a circle or pointer,
- The video of the unknown individual would be flagged, such as by a circle or pointer, and tracked as he/she moved around.
- If a known (or unknown) person is in a field of view, the time and location is logged on a database.
- If it is desired to know where a particular person has been and what they are doing there, the database can be polled and the associated images or video immediately brought up for review.
- If a known individual enters an area that is not accessible by that individual, an alarm condition can be generated.
- The alarm condition can:
- Generate an audible alarm at the area of infringement.
- Generate an alarm at a monitor station.
- Switch the video to the monitor station.
- Start video tracking of the individual.
- Log the video to a server.
- Log the locations pursued to the server.
- Log the time for each of the locations.
- Example—in a school, if a student is supposed to be in a particular classroom at a particular time, if he is found in other areas an alarm event can be generated.
- The system can log all areas that an individual visits.
- The system can show individuals on a map:
- By an Icon
- By Name
- By a small photo of their face
- By Function (nurse, doctor, security, maintenance, student, Freshman, Senior, Teacher, Coach, Administration, Security, etc.).
- By Department (Maintenance, Library, Engineering, etc.).
- Clicking on the icon on the map for each person can give more data if it is not presented on the map display:
- Name
- ID Number
- Department
- Rank
- Student schedule
-
FIG. 1 depicts prior-art Facial Recognition systems. InPrior Art # 1,video camera 1 views a scene of interest, andprocessor 2 analyzes the video signals produced by the camera. The processor performs the steps of: -
- Facial Separation, e.g., locating human faces within the viewed scene,
- Facial Signature generation, e.g., deriving a unique identifying descriptor for the detected faces,
- Database Creation, adding said descriptors and separated facial image to a comparison database,
- Database Lookup, matching the captured descriptors with previously-captured faces or images containing faces or other relevant data, and
- Generating alarms as appropriate.
- In
FIG. 1 , the basic function of the system can be enhanced as depicted inPrior Art # 2. As shown, the processing function has been divided among several processors. One ormore processors 3 perform the computationally intensive tasks of Facial Separation and Facial Signature generation, while processor 5 performs the less demanding task of database pattern matching. This yields improved system economies and flexibility: cameras and Facial Processors may be added incrementally to the system as needed, and it is unnecessary for each Facial Processor to contain or to access the entire ‘reference’ database. -
FIG. 2 depicts the application of the basic Facial Recognition technology to a networked surveillance system. Important aspects and features of the system and described in detail herein are the following: -
- IP Video Cameras Driving Facial Recognition.
- Networked IP Video Cameras Driving Facial Recognition.
- IP Video Cameras Driving Networked Recognition.
- Networked LP Video Cameras driving both Image Database and Network Recognition.
- Use of MPEG I-Frames from Stream to drive Recognizer.
- Use of High-Resolution Still Streams to drive Recognizer.
- Use of Multicast to send Motion Streams to Monitor and Recognizer simultaneously.
- Use of Multicast to send Still Streams to Monitor and Recognizer simultaneously.
- Tagging of archived images in the database, where faces have been located on that image, with the all of the “facial signatures” of individuals seen in that image. Note that these signatures may be of known or of then unknown persons. This can be done in real-time or post processed.
- In the system of
FIG. 2 , and labeled “IP # 1”,Camera 20 is an “IP camera”, as distinct from the conventional analog camera in the prior art. This IP camera perform additional processing steps to the captured video; specifically the captured video is digitized, compressed into a convenient compressed file format, and sent to a network protocol stack for subsequent conveyance over a local- or wide area network. Typical compression schemes include MPEG, JPEG, H.261 or H.263, wavelet, or a variety of proprietary compression schemes. A typical network topology is the popular Ethernet standard, IEEE 802.3, and may operate at speeds from 10 Mb/s to 100 Mb/s. Network protocols are typically TCP/IP, UDP/IP, and may be Unicast or Multicast as dictated by the system requirements. - The cameras' compressed digital video is transported via Local Area Network (LAN) or Wide Area Network (WAN) 21 to a
processor 22 which performs the steps of Facial Separation, Facial Signature Generation, and Facial Database Lookup. - The utility of the system may be enhanced by the increased use of modern networking techniques, as
FIG. 2 depicts in diagram “IP # 2”. In this enhancement, a group ofnetworked processors 25 perform the steps of Facial Separation and Facial Signature generation. This is distinct from the network topology ofFIG. 1 , in which specific Facial Processors are dedicated to specific cameras. InFIG. 2 , theFacial Processors 25 are treated as network resources, and are configured to process video from any networked camera as required. This improves the flexibility and economics of the system. For example, during periods when a particular area is not used, Facial Processors may be diverted from analysis of that particular camera to an area of higher traffic. Also, the workload of a failed Facial Processor may be diverted to a different processor. - Other benefits arise from the topology of
FIG. 2 . For example, theFacial Database 24 may be treated as a general-purpose network resource, allowing a greater number ofcameras 20 andFacial Processors 25 to perform Facial Signature lookups at any given time. Moreover, the digital IP surveillance network is often part of a larger “network of networks”, thus allowing the Facial Database to be consulted by devices on a different network. This is useful in cases where different organizations may have compiled different Facial Databases. For example, an airport may maintain a database of the Facial Signatures of all current employees, as well as of past employees. A law enforcement organization may maintain a separate database of known offenders, and an Intelligence organization may maintain a current database of foreign nationals of interest. In the depicted networked environment, theFacial Processors 25 may consult several different Facial Databases, across the LAN or WAN. - An additional benefit of this topology arises from the fact that IP surveillance systems often maintain an archive 23 of stored video or images. Since this archive is generally available on the network, it is possible to use the system to search for faces in archived images, during event reconstruction. For example, the IP surveillance network of
FIG. 2 stores captured images or video in an Image Database 23. Often, these images are captured only when the associated camera has detected motion within its field-of-view, thus reducing the storage requirements of the image archive platform. Since the Image Database 23 is a generally-available network resource, it is thus possible to perform the Facial Processing on these stored images as well as on live camera video. - For example, the
Facial Processors 25 andFacial Database 24 detect the presence of a person of interest in some live scene. Using the image archive, it is possible to track the person's movements backward in time, thus re-constructing the person's movements through a facility. It is additionally possible, for example, to note whether the person-of-interest may have made contact with other people within the area being monitored. The system may then, upon command, derive a Facial Signature from that ‘new’ person's image, and add that new Facial Signature to the Facial Database. Historical analysis of the ‘new’ person's movements through the facility may then be performed, or the real-time location and movements of the ‘new’ person may be tracked. -
FIG. 2 depicts the Facial Database and the Image Archive as two distinct platforms, both resident on the LAN or WAN. It should be noted that these functions are essentially software, hence both functions may be resident on the same physical platform if system requirements so dictate. -
FIG. 3 depicts a further extension of the invention ofFIG. 2 . InFIG. 3 , the IP cameras 30 have been enhanced with additional processing resources, and are capable of performing the Facial Processing internally. The separate Facial Processors of the previous example are eliminated. In addition, this approach allows improvement of the storage efficiency of theImage Database 34, since images may, if desired, only be stored in the Image Archive if a face is recognized by one of the cameras 30, or if a particular predetermined face is detected byFacial Database 33. - The previously listed and incorporated applications and patents have described a surveillance system wherein the IP cameras may produce multiple video streams as the system requirements may dictate. For example, in
FIG. 4 theIP cameras 40 may produce several motion MPEG video streams with different bandwidths (for different audiences), and may additionally produce a high-resolution still frame JPEG image for storage in an image database 45. Note that the system ofFIG. 2 may utilize any of these video streams for facial recognition. Since thecameras 40 are IP-based, their motion video and still frame video streams are generally available upon demand throughout the network, and either type of video may be used to drive the Facial Recognition system. The still frame images have the advantage of greater resolution, but may be generated less frequently. Motion video sources may produce useful images more often, but at a reduced resolution. This reduced resolution decreases the accuracy of the Facial Recognition process. - The previously listed patents and applications also describe the use of Multicast protocols to support the one-camera-to-many-viewers nature of the surveillance system without duplicating network traffic. This Multicast network protocol lends itself well to the present invention. The Facial Processor is simply another ‘viewer’ on the network and no additional network traffic need be generated for it. Multicast protocol is used to convey the motion video, and Unicast protocols to convey the still-frame images to the image database. In the present invention, the still-frame images may also be conveyed over the network as Multicast data, since there is more than one recipient of the still images.
-
FIG. 4 depicts the overall integration of the Facial Recognition technology with the IP camera network.IP cameras 40 produce a variety of real-time data streams as shown. Motion video may be compressed into two simultaneous transport streams, such as a low-resolution QSIF stream and a higher-resolution SIF stream. SIF is normally 352×288 resolution, and QSIF is normally 176×144 resolution. Audio may be captured, digitized into a low-bit-rate stream for transport over the network. In addition, the still-frame images may be captured at a high resolution, say 704×480, and compressed into image files sufficiently small as to meet system requirements. These still-frame compressed image files may, as previously described, be conveyed by the network 47 as a Multicast stream, or as a pair of Unicast streams. -
FIG. 4 also depicts the remainder of the surveillance network.Monitor stations 41 and 44 are configured to display the scenes captured by one or more of thenetworked video cameras 40. The monitor station may display one camera, or may display four cameras in a 2×2 array, nine cameras in a 3×3 array, or sixteen cameras in a 4×4 array. To conserve system bandwidth and the monitor station's processing capacity, larger arrays such as 4×4 display the low-resolution QSIF streams, while the single-camera array displays the selected camera's SIF output. -
FIG. 4 additionally depicts a ‘wireless’monitor station 43, which receives selected video streams from the network viaWireless Access Point 42. Due to the bandwidth constraints typical of wireless systems, a QSIF stream is normally displayed in the application. Such a wireless monitor station is typically used by guards or other law enforcement personnel who require mobility. -
FIG. 4 also depicts an image server 45. This server receives and stores still-frame images produced bycameras 40, for subsequent retrieval and analysis. These still-frame images are ordinarily produced only when the associated camera has detected motion within its field-of-view. Server 45 may additionally be configured to store motion video streams upon detection of motion within its field-of-view. - A Facial Database 47 is depicted in
FIG. 4 . As previously described, this processor contains a stored database of the Facial Signatures and associated mugshots of some previously-defined persons. - Finally,
FIG. 4 depicts the networkedFacial Processors 46, which detect faces within selected camera's captured video, and which subsequently derive unique Facial Signatures from the detected faces. Facial Signatures thus detected are forwarded to the Facial Database 47 for correlation with a previously stored ‘library’ of facial mugshots, associated Facial Signatures, and database images in which the current Facial Signature was previously detected. -
FIG. 5 depicts a typical structure for an Image Database and a Facial Signature Database. The Image Database stores captured still images from the various IP cameras within the network. Each captured image is stored in some predetermined location within the server's file system. Each such image is represented by a unique Image ID number, maintained in a database file. Within the file, each record contains the Image ID number, as well as related data such as the date and time the image was taken, physical location where the image was taken, which camera captured the image, a fully-qualified URL describing where the image is located, and any facial Signatures which were detected within the image. - In a typical structure for the Facial Signature Database, each unique Facial Signature file contains the Facial Signature data, the subject's name if known, age, weight, aliases if any, URL of a mugs hot or separated facial image, URL of a biographical file if any, and image ID numbers of any Image Database records which contain the current Facial Signature.
- Previous Figures have depicted the presence of a networked Monitor Station. A typical screen layout of such a Monitor Station is depicted graphically in
FIG. 6 . AMap Pane 61 contains a map of the facility under surveillance. This Map Pane may contain multiple maps, possibly representing different floors or buildings within a facility. Different maps may be displayed through common ‘point and click’ methods. Each map contains graphical icons representing the location and ID's of the various IP cameras available on the network.Video Pane 62 contains the current video of the selected camera or cameras. When viewing stored images from the Image Database, this Video Pane displays selected images from the database. AControl Pane 63 presents a variety of context-sensitive GUI User controls. - With the Facial Processors and the Facial Database available on the LAN or WAN, a number of useful and novel applications become possible.
- Within a facility, the various IP cameras view scenes of interest, and one or more Monitor Stations display video from a selected group of cameras. Facial Processors locate faces in video from selected cameras, and derive Facial Signatures from the detected faces. These Facial Signatures are transmitted to a Facial Database, which searches through its stored Facial Signature library for a match.
- When the Facial Database scores a ‘hit’, it forwards appropriate information to the networked Image Database server. This information includes:
-
- The camera ID and image ID in which the match was found
- The location within the image where the matching face is located
- The stored Facial Signature which matched
- The stored mugshot associated with the Facial Signature
- Related information associated with the Facial Database record, such as the person's name, age, employer, criminal history, etc.
- Upon receipt of this data, the Image Database server may perform the following steps:
-
- The server appends the descriptive information from the Facial Database to the current image that contained the hit.
- The server forwards the ‘hit’ information to all Monitor Stations on the network. The Monitor Stations thereupon bring the current image, containing the Facial Match, to the forefront of the application screen.
- Monitor stations additionally display the matching face from the database, plus other descriptive information provided by the database.
- The ‘hit’ event is added to the system log.
- The server likewise alerts any mobile or wireless Monitor Stations of the presence of the ‘hit’ and it's location.
- The server forwards the matching face and related descriptive information from the Facial Database to the wireless Monitor Station for display.
- The server alerts appropriate personnel from a predetermined list, using e-mail, pagers; or an automated telephone message.
- The server may additionally send a message to an associated facility security system, which thereupon locks entry doors as appropriate.
- When the system is enhanced with Facial Recognition technology, a number of useful and novel functions may be added to the basic surveillance system. The basic functions are as follows:
-
- “Hit” is automatically located on map. Map is brought forward automatically if required.
- A moving “Hit” is tracked on the map.
- “Where is” our person—Locating individual personnel by query, such as security guard or maintenance personnel. Key in query, response is location, map location, and/or video of his location.
- “Where is” Security Guard tracking and logging of locations present and time of presence in database.
- Alarm condition if guard is not seen at specified location during rounds by predetermined time.
- “Where is” Lost Child implementation—local scanner input of photo, activate recognition function.
- Automatic tracking of manually “Tagged” personnel of interest searches forward in real time, backwards in database. Graphical User Interface for “Tagging” suspect of interest.
- Use of Image Database—find an unknown suspicious person or person perpetrating an event and “cut” their facial image, reduced it to its signature, then do “find”.
- The “find” above can be done in real-time to find the person at the present time in the facility.
- In real-time, if not found, set “trap” to add to APB (define) list for future ID. Upon finding individual, alarm event is notified, and attached notes as to incident and images can be brought into focus.
- The “find” above, can be done against the database, either an image or a signature database, to find other instances that the individual was on premises, and see what he was doing.
- The “find” can either look against stored facial signatures, or against stored raw images that are analyzed during post-processing.
- When the Facial Database detects a ‘hit’, the location of the hit is depicted on
map pane 61 ofFIG. 6 . The appropriate map may be brought forward, if not already displayed, and the associated camera icon is highlighted, flashed, or otherwise made visually distinct. The subject person's current location within the facility is thus displayed. As subsequent hits are detected, possibly at a succession of cameras if the person is in motion, the associated camera icon is again highlighted, indicating the person's movements. - Inquiries regarding the current location of individual personnel may be performed by the system. As an example, a previously-enrolled person is selected from the Facial Database, using the person's name, mugshot, employee ID, or other stored information. This selection may be made from a Graphical Interface on a networked Monitor Station. The Facial Database is then instructed to look for a ‘hit’ on that record. When one of the networked IP cameras captures an image, subsequently determined by a networked Facial Processor to contain that person's face, the Facial Database informs the Monitor Station of the match. The Monitor station may then highlight the camera icon of the associated camera, effectively locating the desired person on the map. The Monitor station may additionally bring that camera's video to the forefront, displaying a current image of the desired person.
- In an enhancement of this application, the desired person's movements may be compared against a known route, schedule, or database of approved/restricted locations. For example, a security guard may have a predefined route to cover, which defines locations and times of his rounds. The Facial Database may be instructed to look through real-time images for a match with this person. If any such matches are found, they are compared with the times and locations defined by the guard's predefined schedule. If the guard successfully follows his usual rounds, the Facial Database can log this in a security log, including times and locations of the guards' route. If, however, the guard is not detected at the predefined location and/or time, this fact may be logged and, optionally, a system alarm may be generated to notify appropriate security personnel. Additionally, it is possible for the system to detect any non-approved persons in those areas, and generate an alarm. For example, a night guard may have a predefined set of rounds to cover. The system may detect the presence of the guard at the correct times and locations, and note this in a log file. Detection of the guard would not cause a system alarm, however, the detection of any other personnel at those times and places would generate an alarm. Likewise, detection of that guard at an unexpected location or place would generate an alarm. Note that it is not necessary for said ‘other’ personnel to have been previously enrolled in the database; the mere detection of any Facial Signature other than that of the predefined guard would generate a system alarm.
- In a Hotel application, hotel guests may be enrolled into the system at the time of registration. Hotel employees may likewise be enrolled into the system at the time of their employment. The system may be instructed to log the time and location of each successful facial detection, whether a database ‘hit’ occurs or not. If the facial detection does not match any person enrolled in the Facial Database, the system may generate an alarm, and indicate on a networked Monitor Station the location, and live video, where the face was detected. By way of example, common hotel burglars are thereby automatically detected and recorded by the system, and the system can be instructed to generate an alarm upon the next occurrence of this person. On the other hand, if the detected face is enrolled in the Facial Database, the system may determine what action to take based upon a pre-defined set of rules. For example, if a previously-enrolled guest is detected on the correct floor, then the event is logged but no alarm is generated. If the guest is detected on the wrong floor, the event is logged and an alarm may or may not be generated based on a pre-defined qualifier. An employee may be detected, and an alarm may or may not be generated based on the employee's schedule or authorizations. For example, a cleaning lady on the correct floor at the correct time would not generate an alarm, but the same person on the wrong floor may generate an alarm.
- In an airport security application, all persons who successfully pass through a security checkpoint are photographed and enrolled into a networked Facial Database. In addition, the person's itinerary is recorded into the database. This Facial Database may then be shared among several airports. Thus, in any airport:
-
- Detected faces that do not match any Facial Database entry may generate an alarm, directing security personnel to the location of the ‘unknown’ person, and may cause a suitable networked monitoring Station to display the real-time video.
- Detected faces that match an approved passenger in the Facial Database may be compared with the person's itinerary for that trip. If the passenger is in some location or airport that does not match the passenger's itinerary, then security personnel may be alerted to the person and to their location.
- Personnel who attempt to board an aircraft without having been enrolled into the Facial Database may generate an alarm, and may be detained by security personnel.
- Airport employees who may be in unauthorized areas, or who may attempt to approach or board an aircraft, may generate an alarm to appropriate security personnel.
- In a useful enhancement of this application, a previously unknown person may be ‘enrolled’ into the Facial Database, and a facility-wide search may be commenced. A lost child, for example, may be enrolled into the system through the use of a photograph scanned into the Facial Database. In lieu of a photograph, all children entering some facility, such as an airport or theme park, may be photographed and enrolled into the Facial Database. The Facial Database may then search all real-time camera video for a match with the enrolled child. When a networked IP camera produces video which is subsequently determined to contain the lost child's face, one or more networked Monitor Stations alert security personnel of the event, and provide location and camera video of the lost child. Security personnel may then be dispatched to the location of the child.
- Other applications of personnel tracking may require that a person be manually ‘enrolled’ into the Facial Database. For example, a person seen in a live image may be ‘tagged’ by an operator at a Monitor Station, whereupon the ‘tagged’ person's Facial Signature is added to the Facial Database. This is accomplished through the use of a GUI, wherein a specific still-frame image (or a frozen frame from a moving image) is displayed to the Monitor Station operator. The operator selects the desired face from the displayed image, through the use of a mouse or equivalent pointing device. The selected face is then separated from the image, the Facial Signature is derived, and the Facial Signature is added to the Facial Database. The operator is prompted to provide other pertinent information as appropriate to the application, such as a description of the observed event.
- The Facial Database may then be instructed to flag an operator whenever the ‘tagged’ person's image appears in any of the real-time images captured by the networked IP cameras. If the ‘tagged’ person's face is not observed by the Facial Database within some predefined time interval, then the Facial Database may be instructed to add the person's Facial Signature to a ‘watch list’ within the Facial Database. If the person's Facial Signature is subsequently detected by the Facial Database, then an alarm is generated, and selected Monitor Stations ‘pop’ the relevant information onto the Monitor Screen.
- Alternatively, the Facial Database may be instructed to search through the Image Database for all occurrences of the ‘tagged’ person's Facial Signature. This search may be made against the Image Database, or against the Facial Signature database, which keeps a record of all image filenames in which the selected Facial Signature occurs.
- The invention has applications in day-to-day law enforcement:
-
- Police car has on-board suspect database or link to database. When an officer stops a suspect, lookup occurs.
- A policeman sees a suspicious person, it is logged into a database along with notes from the officer. That information is then disseminated to other officers using facial key. If that suspect is encountered again by the same or a different officer, previously collected information will be available.
- The surveillance network may include the use of wireless, mobile Monitor Stations as well as the use of wireless IP cameras, all of which are part of the overall IP surveillance network. A patrol officers squad car may be equipped with both a wireless IP surveillance camera, as well as a wireless Monitor Station. When an officer stops a suspect, the suspect's image may be captured by the car's wireless surveillance camera. The captured image may then be forwarded to a networked Facial Processor, which derives a Facial Signature from the suspect's image. This Facial Signature may be forwarded to the Facial Database, which looks for a match between the suspect's Facial Signature and any Facial Signatures which may have been previously recorded. Thus, Suspects may be quickly and accurately identified during the stop.
- In another application, a suspicious person's image is captured by a wireless IP surveillance camera, and the Facial Signature is generated as before. The Facial Signature is stored in the Facial Signature database, along with other information collected by the officer, such as location, time, type of activity observed, and so on. This information is then available to other officers via the Facial Signature database. If another officer encounters the person, the person's image may be again captured, and the ensuing Facial Signature match may alert the officers as to the previous suspicious activity. In this way, a person's behavioral pattern may be easily and systematically detected and recorded, such as a person who may be ‘casing’ a bank prior to a potential robbery.
- The surveillance network, as supplemented with the Facial Recognition technology, finds usefulness in daily attendance applications:
-
- Students logged in to class and time stamped. By comparison to schedule database, create Automatic Absentee and Tardy logging and notification.
- Automatic correlation of absent and tardy people that are found in other areas. Alarm conditions can be generated, video selected on monitor stations, icons brought up on maps.
- For example, an IP camera may be trained at a classroom doorway, so as to capture facial images of attendees. Alternatively, the camera may be positioned to view the entire room. In either case, the images thus collected may be used to find faces, derive Facial Signatures, and compare a list of persons present to a class schedule database. This effectively automates the process of attendance taking. The system may thus record attendees, plus absentee or tardy students.
- The system may additionally correlate the real-time list of tardy or absent students against Facial Signatures of students detected in other areas of the school. In the event of a database ‘hit’, the system may generate an alarm, and display the surveillance image of the student. The Monitor Station may additionally display relevant student information, such as name, current location, classroom where the student is scheduled to be, or prior attendance information.
- In secure areas where access by authorized personnel is strictly controlled, the system has important applicability both in monitoring and in controlling access. Features include:
-
- Known personnel approved for specific area access are not alarm events if seen. All others are alarm events.
- Known personnel approved for specific area access at specific times and dates are not alarm events if seen. All other personnel are alarm events, or known personnel outside of approved area at approved time are alarm events.
- Hotel Example: Registered guests and hotel personnel logged into database. Tracking of areas covered logged, but not alarmed. All others tracked and alarmed. Time and area qualifiers also may be used, such as a guest on the wrong floor.
- Multi-Level Alarms, such as a registered guest on the right floor would be a condition green, on a wrong floor would be a condition yellow, a fired employee any place in the building would be a condition red.
- Airport/Transportation application: A problem is people in airports skipping or passing security in smaller airports where security is minimal, then flying to a major airport and having full access to flights (connections) without further security checks. The present invention addresses this by capturing an image of every person who is security checked at any facility. Their facial signature is then added to the “OK” list for that day, or for that specific itinerary and time frame. The facial signature can then be forwarded to other airports. In those airports, if any individual appears behind the security check area who has not been properly cleared by security, then an alarm is generated so that individual can be investigated. Personnel, such as airport employees, who try to board planes without being passengers or passing through appropriate security can also be apprehended by use of cameras monitoring boarding.
- My previously mentioned applications and patents describe a personal ‘Panic Button’, to be used by teachers or other personnel who may need to alert security personnel during an emergency. The addition of Facial Recognition technology to the networked surveillance system, also previously described, enhances the utility of the Panic Button.
- Personnel carry a radio transmitter with a button. When an event button is pushed, the transmitter relays to a receiver that relays to the network the type of event (security request, medical request, fire request, etc.) and the individual who generated the event. The facial recognition system would then look for the last known location of that individual, and identify the event in that area—such as map indication, camera selection, and response personnel dispatch.
- In an example application, the panic button transmitter may contain one or more pushbuttons labeled, for example, ‘FIRE’, ‘MEDIC’, “POLICE' and so on. When the user presses a button, an internal processor composes a message which encodes the identity of the person and the nature of the emergency (as derived from which button was pressed). This message is then transmitted to one or more networked receivers, and is displayed on one or more Monitor Stations. Security personnel may then be dispatched to the person's location as required.
- It is often difficult to determine, with any accuracy, the exact location of the person who signaled the emergency. With RF-based systems, the location of the transmitter may only be determined to within the working radius of the receiver(s) that detected the transmission. Typically, such receivers have a fairly broad coverage area, so as to minimize the total number of receivers required to completely cover the facility. Thus, localization of the person sending the alarm is of poor accuracy.
- With the addition of Facial Recognition technology to the network, this problem is solved. When a networked Panic Button receiver detects a transmission from a known person, the Facial Database looks up the person's Facial Signature, and proceeds to search all incoming video for a match. This localizes the person to within the field of view of one particular camera. The system additionally displays the current video from that camera.
- Moreover, if the Facial Database fails to detect the person's Facial Signature in any current video, then the Facial Database may be instructed to search the Image Database for the person's image. Such a search would start at the most recently stored images, preferably starting with previously known locations, if any, where the person was scheduled to have been. When a match is detected, the Monitor Station may be instructed to display the most recent image containing the person's image.
- Certain types of security alarm events may require the dispatch of specific types of personnel:
-
- Events that require response, such as fire alarms, alarm system triggers, facial recognition “hits” on suspects can be geo-located by some means, such as fixed sensors at known locations, or facial recognition events. When the location of such an event is determined by the system, the location of appropriate response personnel based on last known facial recognition can be utilized. For example, if a “security” panic button is pushed and location determined, the closest security guard to the area of the alarm as determined by the facial recognition system can be dispatched.
- Use of Access Point determination communication links to a mobile guard station will identify area that the guard is in. Dispatch of closes response person can then be accomplished.
- For example, a fire alarm might require the immediate dispatch of firefighters, while a medical alarm might require the immediate dispatch of a nurse or doctor. A security violation at an entrance door may require the dispatch of a security guard.
- It may be difficult to provide such immediate personnel dispatch if the location of the various personnel is not known. Addition of Facial Recognition technology to the networked security surveillance system eases, and may indeed automate, such dispatch.
- In such a system, all security, fire, medical, or administrative personnel, for example, are enrolled into the Facial Database. Upon detection of a particular type of system alarm, for example a fire alarm, the Facial Database is instructed to search all incoming video for a Facial Signature match with one of a group of pre-enrolled firefighters. When the Facial Database successfully detects one or more of these firefighters, their current location is indicated on the Monitor Station. This indication may be via graphical icons on the facility map, or by displaying the camera(s) which contain their video. In either case, the available firefighters are located, and the nearest ones can be dispatched to the scene of the fire.
- Previous examples have mostly involved the use of a pre-defined database of Facial Signatures. Other applications of the system may involve the use of a Facial Database that is collected over a period of time.
- Databases of individuals can be built-up automatically. Link of the surveillance system, with other systems such as ATMs, ticketing systems, and the like can be made. As an individual does a transaction his facial signature is logged. If another transaction is attempted but a different facial signature is involved, and alarm is generated.
-
- A person's image and Facial Signature may be collected as part of a routine transaction, and added to a Facial Database for later use. This approach has merit in transactions involving ATM's, ticketing systems, gas pumps, banking, or a variety of over-the-counter purchase transactions.
- By way of example, airline tickets are used under a specific name and a facial signature and an image are collected. If the same name is used again, but a different facial signature is seen, an alarm event is generated. The use of the previously captured image can be utilized for operator intervention to determine what has happened.
- Conversely, if the same facial signature shows up again in another transaction, but the name is different, an alarm event is generated and the subject investigated. The use of the previously captured image can be utilized for operator intervention to determine what has happened. This could be a terrorist attempting to travel on a stolen ID, or could be a recently married lady whose name changed. The image can verify it is the same person, investigation would have to address changing names.
- In another example, an ATM card or Credit Card is used. The system captures a facial signature for that specific card. An image of the user is captured and stored as well. If that card is used but a different facial signature is seen, and alarm event is generated. The use of the previously captured image can be utilized for operator intervention to determine what has happened.
- In yet another example, prescription drugs are purchased under a specific name and a facial signature and an image are collected. If the same name is used again, but a different facial signature is seen, and alarm event is generated. The use of the previously captured image can be utilized for operator intervention to determine what has happened.
- Note that in these cases, where a valid credit or ATM card is used but the Facial Signature does not match prior transactions, the Facial Database alerts other linked systems to perform a search for any transaction involving that ATM or credit card. Alternatively, the Facial Database alerts other security networks to search any available camera video for that person's Facial Signature. Thus, after a person uses a stolen ATM card at one bank, the person's Facial Signature may be forwarded to other banks in the area, which may be instructed to search for any ATM transaction, or any camera video at all which contains the selected Facial Signature.
- An area can be monitored for repeated (suspicious) access by specific but unknown individuals. If the repeated access is over a selected threshold point, an alarm can be indicated. Images can be stored with attached facial signatures. A search of that facial signature would then bring up all images of that individual.
- For example, a bank can have a facial database of all current customers and bank personnel. If an unknown individual appears in the recognition system several times without becoming an employee or customer, this could create an alarm condition. A search by facial signature can go back in the database and allow investigation of what that individual was doing. If it is a known benign individual, such as the postman making mail delivery is seen, a GUI can allow “tagging” that individual from unknown to known. This would prevent generation of future alarms when that particular individual is recognized.
- Networked security surveillance systems such as described may use Facial Recognition methods to spot developments or trends that may be of interest. For example, a bank's surveillance network may automatically detect and enroll all faces captured by its network of security cameras. The Facial Database may then be searched for trends, such as a new face that appears on the scene and which becomes persistent or periodic. The Facial Database may then alert security personnel to these detected patterns, via a networked Monitor Station.
- Most of these cases will be benign, such as the Postman or perhaps a construction crew doing renovations. An operator at a networked Monitoring Station may add an entry to the Facial Database which defines these regularly-detected Facial Signatures as ‘approved’, along with appropriate identifying information.
- Some of these cases, however, might be people reconnoitering the premises in preparation for a crime. Upon detection of such a person, security personnel may be notified via a networked Monitoring Station, and personnel may be directed to intercept the person immediately, or upon the next detection of the person. In addition, the Image Database may be searched for any occurrences of that person's Facial Signature, as part of the event analysis.
- In this application, a networked camera captures a person at a door camera, the recognizer identifies the individual, a database lookup occurs to see if that individual is authorized for access at that time and place, access is allowed, a signal is sent to an electric door strike or other control device to allow access.
- In the invention, doorways are each equipped with a networked IP surveillance camera, positioned to capture the face of the person seeking entry. When a face is detected at a particular doorway camera, the Facial Database searches for a match between the detected person's Facial Signature, and a Facial Signature in the Facial Database. If the detected person's Facial Signature is found in the Facial Database, on a list of ‘approved’ persons, the Facial Database commands the electric door ‘strike’ to open and allow the person entry to (or exit from) the facility.
- Many locations experience problems with curfew violations, where underage persons are present at prohibited locations, or are in public locations after some predefined time. The networked surveillance system, enhanced with Facial Recognition capabilities, may be configured to automate detection of such violations.
- A database of affected personnel such as students or minors is created. This can be done at schools, or by means of photos on driver's licenses, for example. Cameras patrolling common street areas are deployed with facial recognition. If such people are detected in the street after curfew time, an alarm is generated and response personnel dispatched.
- In the invention, a number of IP cameras are positioned around some area known to be frequented by curfew violators. The networked Facial Database may be loaded with still-frame images and Facial Signatures of underage persons, perhaps from a Facial Database generated by the public schools, or from a Juvenile court, or the like. When the Facial Signature of a captured face matches a face in the Facial Database, police or other appropriate personnel may be dispatched to the location.
- The system may also be interfaced to a point of sale system, such as a gasoline pump. An image of the person activating the pump is collected. If that individual leaves the store without paying, the facial signature and image of that individual is added to the “drive-off” list. If that individual returns to that store, the pump will be locked out and personnel can be notified of a former drive-off suspect. In addition, drive off facial signatures can be forwarded to other stations to prevent that person from accessing pumps at other locations, and assist in apprehending that person.
- Retail establishments can collect images in conjunction with retail transactions such as use of membership cards, checks or credit cards. A facial signature of the associated image is generated. If the transaction “goes bad” the facial signature can be so noted and shared with other retail establishments. This can be within one company, it can be a cooperative service with many members, or it can be an extension of check and credit card verification services. This prevents multiple use of stolen or forged checks, credit cards, and the like.
-
FIGS. 7 through 15 depict a comprehensive integration of the networked video surveillance system with Facial Recognition technology and with commonplace or legacy airport security measures. These airport security measures include metal detectors, baggage X-ray scanners, scales, and related devices. An integrated network of said devices improves security throughout the air travel system. -
FIG. 7 depicts the overall network.Various airports 70 each contain a Local Area Network (LAN) to interconnect their various security equipment. Each airport is equipped, for example, with Networked Security Cameras at the curbside check-in point(s) 75, at the ticket counter(s) 76, the security screening point(s) 77, the various gate counters 78, and at the entrance to each jetway 79. In addition, the airport facility is equipped with a group of Networked Surveillance Cameras, providing surveillance coverage of other areas of interest, including concourses, restaurants, baggage handling areas, aircraft loading areas on the tarmac, and so on. These Airport LANs are all interconnected via a national Inter-Airport WAN 71, permitting efficient dissemination and sharing of security data betweenairports 70 and with en-route aircraft 74 via ground station/satellite communications link 73. -
FIG. 8 depicts the airport network in greater detail. Networked Surveillance Cameras 80A through 80E are stationed at the various security checkpoints as indicated, including curbside check-in, ticket counters, security checkpoints, gate counters, boarding gates, and so on. The Airport Security LAN contains Networked Monitoring Stations 85, Networked Facial Processors 86, Networked Image Database 87, and a NetworkedFacial Database 88. In addition, the Airport LAN has a connection to the National Airport Security WAN. Additional Networked Surveillance Cameras 80 are installed in various areas of interest within the airport as previously discussed. In addition to the cameras, the security checkpoints contain other Networked devices as appropriate to the function of the checkpoint. For example, at curbside check-in, scanner 81A is used to scan a departing passenger's photo ID and ticket, and thereupon store such captured information into the airport's networked Image Database. At the ticket counter, a scale 82A and explosive sensor 83 are used in screening passengers, again storing such captured information into the networked airport Image Database. -
FIG. 9 depicts typical apparatus used at curbside check-in.Passengers 91A and 91B arrive at curbside for check-in. Networked Surveillance Cameras 90A and 90B capture their image, for subsequent Facial Analysis and enrollment into the airports Networked Facial Database. Their baggage, 92A and 92B respectively, is additionally photographed by cameras 90A and 90B, and is weighed by anetworked scale 93, and the resulting weight reading is stored in the airport's networked Image Database along with the passenger's captured Facial Signature. Additionally, the passenger's Photo ID and tickets are scanned with networked scanner 95, and the resulting images are additionally stored in the airport's networked Image Database. -
FIG. 10 depicts a typical arrangement at a ticket counter.Passenger 103 arrives at the Ticket Counter for ticketing and baggage check.Networked Surveillance Camera 100A captures the person's image, for subsequent Facial Processing and Image storage. The passenger's baggage is weighed by networked scale 101, and the baggage is imaged by networked surveillance camera 100B. The baggage's image and weight are transferred viahub 104 to the Airport LAN, and subsequently to the networked Facial Database, and are appended to the passenger's file record in the Facial Database. Additionally, the passenger's ticket and photo ID (driver's license, passport, or the like) are scanned by networked scanner 102, and the resulting images are transferred, via the airport LAN, to the networked Image Database. Other ticket-counter scanners, such as an explosives sensor, an X-Ray scanner, or ascale 105 for weighing the passenger, likewise produce data which are appended to the passenger's record in the Facial Database. - At this point, the person's Facial Signature (as derived from
camera 100A′s captured image) may be compared with the Facial Signature derived from the person's photo ID scan, for identity verification of the passenger. In addition, data describing the passenger's baggage has been captured by the system and stored in the passenger's Facial Database file, for subsequent bag and identity matching. -
FIG. 11 depicts the equipment at a typical entry point for checked baggage, such as at the ticket counter. A networked image scanner captures the passenger's photo ID, which may be a driver's license or a passport.Camera 111A captures an image of the passenger and baggage at that time, and the ensuing Facial Signature may be confirmed against the Facial Signature derived from the passenger's photo ID. The passenger's checked baggage is scanned byX-ray scanner 113, and the X-ray imagery thus produced is captured byNetworked Surveillance Encoder 112, and subsequently appended to the Passenger's record in the Facial Database. An additional Networked Surveillance camera 111B images the passenger's baggage as it leaves the X-ray scanner, and the resulting image is appended to the networked Image Database. A networked explosives sensor 115 likewise produces data descriptive of the baggage, and is likewise appended to the networked Image Database. -
FIG. 12 depicts the equipment at a typical security checkpoint used for passenger screening. Passengers arrive at the security checkpoint and deposit their carry-on baggage on the conveyor belt ofX-ray scanner 123. At that time, they are photographed bynetworked surveillance camera 121A. The image is stored in the network's Image Database, and a networked Facial Processor derives a Facial Signature for the passenger. This data is appended to the existing record in the Facial Database representing that passenger. Additionally, at this time the passenger's photo ID and ticket are scanned intonetworked scanner 120A, and this data is appended to the passenger's file as well. - A further networked surveillance camera may be used, if needed, at an inspection table, near the passenger metal detector, to capture an image of any personal items from the person's pockets or purse, or other personal luggage, during such an inspection. This image, as well, is appended to the passenger's record in the database. In addition to images from this scan of personal items, data from a networked explosives scanner, and scanned images of the passenger's luggage tag, may be added to the passenger's record in the database.
- Security personnel occasionally encounter personal items of an unknown nature, which may require evaluation and approval by qualified supervisors. To improve the speed of the process, supervisors may review real-time networked video of the personal items on the inspection table, and make necessary decisions without having to travel to the security checkpoint.
- As the passenger deposits his carry-on baggage onto the conveyor belt of
X-ray scanner 123,networked surveillance camera 121B captures an image of the passenger's carry-on baggage, and appends it to the passenger's record in the Facial Database. As the passenger's carry-on baggage is scanned byX-ray scanner 123,networked surveillance encoder 124 captures the scanned image fromx-ray scanner 123, and again appends it to the passenger's file.Networked surveillance camera 121C captures an image of the carry-on baggage as it leaves theX-ray scanner 123, and may optionally be positioned to capture an image of both the carry-on baggage as well as the passenger as they retrieve their carry-on baggage from the conveyor. Again, these captured images are appended to the passenger's file. -
FIG. 13 depicts the apparatus used at a typical boarding gate. Atscanner 130, the passenger's ticket and photo ID are scanned, and added to the passenger's database entry. Additionally, the passenger is photographed bynetworked surveillance camera 133. A facial signature from the passenger's photo ID, and a Facial Signature derived fromcamera 133's captured image, may be compared to verify the passenger's identity. Either or both of these Facial Signatures may additionally be compared with similar entries previously added to the passenger's database record, again verifying the passenger's identity. -
FIG. 14 depicts an aircraft 140 being loaded with checked baggage. Asbaggage 143 is loaded onto the aircraft viaconveyer 142, anetworked surveillance camera 141 captures an image of the bag. In addition, ahandheld barcode scanner 144 captures the data from the barcoded baggage tag. The bag's image is transferred, via the facility's security LAN, to the Image Database for storage. In addition, the baggage barcode is stored in the passenger's file. This allows subsequent matching of baggage, as loaded onto the aircraft, with baggage that had been previously matched to a known passenger. -
FIG. 15 depicts apparatus installed on board a mass-transit vehicle, herein depicted as anaircraft 150. Several cameras, shown as 151, 152, and 153, are positioned to capture imagery of the aircraft interior. In particular, areas of interest are the entryway door(s), cockpit, andpassenger area 154. Video or still-frame images thus captured are conveyed to asatellite communications radio 155, then tosatellite 157 viaaircraft antenna 156. From the satellite, images are forwarded to a satellite groundstation, as depicted inFIG. 7 . - Images captured by on-
board cameras 151 through 153 are forwarded to a networked Facial Processor, which extracts Facial Signatures from faces detected in the various images. These Facial Signatures may then be compared with those Facial Signatures of passengers known to be on the flight. In the case of a discrepancy, such as an ‘unknown’ face present on the flight, or conversely a ‘known’ face missing from the flight, appropriate security measures may be taken. - While certain embodiments and features of the invention have shown and described in detail herein, it will be understood that the invention encompasses all modifications and enhancements within the scope and spirit of the following claims.
Claims (17)
1-18. (canceled)
19. A surveillance system having at least one camera adapted to produce an IP signal, the IP signal being transmitted over an IP network, the system comprising:
the at least one camera having an image collection device configured to collect image data;
the at least one camera having at least one facial processor configured to receive digital image data, the digital image data corresponding to collected image data, the at least one facial processor being configured to execute with digital image data at least one facial recognition algorithm, execution of the at least one facial recognition algorithm with digital image data providing for detected facial image data at least one set of unique facial image data, each set of unique facial image data corresponding to a respective detected facial image present in the digital image data;
the at least one camera being configured to provide to the IP network at least both of the following:
digital image data; and
at least one of the following:
correlation indicia relating to whether at least one set of unique facial image data is correlated with at least one compared facial signature record, and
each set of unique facial image data for communication over the IP network to at least one facial signature processor remote from the at least one camera, the at least one facial signature processor being configured to provide correlation indicia relating to whether at least one set of unique facial image data is correlated with at least one compared facial signature record.
20. A surveillance system according to claim 19 and further comprising:
the at least one camera being configured to compare the at least one set of unique facial image data with at least one facial signature record, the at least one camera being configured to provide the correlation indicia.
21. A surveillance system according to claim 19 and further comprising:
the at least one camera being configured to compare the at least one set of unique facial image data with a plurality of facial signature records, the plurality of facial signature records being contained in at least one facial signature database, the at least one camera being configured to provide the correlation indicia.
22. A surveillance system according to claim 19 and further comprising:
each set of unique facial image data being provided from the at least one camera to the IP network, such that each set of unique facial image data is received by the at least one facial signature processor to be compared with at least one facial signature database without preceding transmission of digital image data from the at least one camera over the IP network.
23. A surveillance system according to claim 19 and further comprising:
the camera being configured to provide to the IP network the digital image data in a compressed format.
24. A surveillance system according to claim 22 and further comprising:
a server in communication with the IP network, the server being remote from the at least one camera, the server being configured to receive each set of unique facial image data.
25. A surveillance system according to claim 24 and further comprising:
the server being in communication with the at least one facial signature database, the server being in communication with the at least one facial signature processor, the at least one facial signature processor being configured to compare each set of facial image data with the at least one facial image database.
26. A surveillance system according to claim 19 and further comprising:
the at least one facial recognition algorithm including at least one facial separation algorithm, the at least one facial separation algorithm when executed producing at least one set of facial separation data, the at least one set of facial image data including the at least one set of facial separation data.
27. A surveillance system according to claim 19 and further comprising:
a plurality of cameras in communication with the IP network for collecting image data at distributed locations.
28. A surveillance system according to claim 25 and further comprising:
the server being in communication with a third party database for at least one of the following:
sending facial image data to a third party,
receiving facial image data from a third party, and
both sending facial image data to a third party and receiving facial image data from a third party.
29. A surveillance system according to claim 19 and further comprising:
a remote station in communication with the IP network, the remote station receiving the digital image data, the remote station being configured to display the digital image data.
30. A surveillance system according to claim 29 and further comprising:
the remote station being configured to display a result relating to correlation indicia.
31. A surveillance system according to claim 19 and further comprising:
a tracking utility for communicating with a plurality of cameras to track movements of an individual, the individual having a correlated facial signature, the correlated facial signature having been correlated with a set of unique facial image data.
32. A surveillance system according to claim 31 and further comprising:
at least one of the correlated facial signature and a set of unique facial image data correlated with the facial signature being communicated across the IP network by operation of the tracking utility.
33. A surveillance system according to claim 31 and further comprising:
the tracking utility being operable to track movement of the individual as the individual moves from a field of view of a camera to a field of view of a subsequent camera.
34. A surveillance system according to claim 19 and further comprising:
a storage device in communication with the IP network for archiving archival data, the archival data including least one of:
at least one set of unique facial image data and the at least one set of digital image data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/606,533 US20100111377A1 (en) | 2002-11-21 | 2009-10-27 | Method for Incorporating Facial Recognition Technology in a Multimedia Surveillance System |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US42809602P | 2002-11-21 | 2002-11-21 | |
US10/719,792 US7634662B2 (en) | 2002-11-21 | 2003-11-21 | Method for incorporating facial recognition technology in a multimedia surveillance system |
US12/606,533 US20100111377A1 (en) | 2002-11-21 | 2009-10-27 | Method for Incorporating Facial Recognition Technology in a Multimedia Surveillance System |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/719,792 Continuation US7634662B2 (en) | 1998-08-28 | 2003-11-21 | Method for incorporating facial recognition technology in a multimedia surveillance system |
Publications (1)
Publication Number | Publication Date |
---|---|
US20100111377A1 true US20100111377A1 (en) | 2010-05-06 |
Family
ID=32511494
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/719,792 Expired - Fee Related US7634662B2 (en) | 1998-08-28 | 2003-11-21 | Method for incorporating facial recognition technology in a multimedia surveillance system |
US12/606,533 Abandoned US20100111377A1 (en) | 2002-11-21 | 2009-10-27 | Method for Incorporating Facial Recognition Technology in a Multimedia Surveillance System |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/719,792 Expired - Fee Related US7634662B2 (en) | 1998-08-28 | 2003-11-21 | Method for incorporating facial recognition technology in a multimedia surveillance system |
Country Status (1)
Country | Link |
---|---|
US (2) | US7634662B2 (en) |
Cited By (69)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040136388A1 (en) * | 2002-12-26 | 2004-07-15 | Schaff Glen D. | Video-monitor/recording/playback system |
US20080226119A1 (en) * | 2007-03-16 | 2008-09-18 | Brant Candelore | Content image search |
US20080232651A1 (en) * | 2007-03-22 | 2008-09-25 | Artnix Inc. | Apparatus and method for detecting face region |
US20090189984A1 (en) * | 2006-08-07 | 2009-07-30 | Ryuji Yamazaki | Object verification device and object verification method |
US20090213221A1 (en) * | 2008-02-25 | 2009-08-27 | Canon Kabushiki Kaisha | Monitoring system, method for monitoring object entering room, and computer readable storage medium |
US20090251537A1 (en) * | 2008-04-02 | 2009-10-08 | David Keidar | Object content navigation |
US20100295944A1 (en) * | 2009-05-21 | 2010-11-25 | Sony Corporation | Monitoring system, image capturing apparatus, analysis apparatus, and monitoring method |
US20110013003A1 (en) * | 2009-05-18 | 2011-01-20 | Mark Thompson | Mug shot acquisition system |
US20110169631A1 (en) * | 2010-01-11 | 2011-07-14 | Ming-Hwa Sheu | Real-time alarm system |
US20110317008A1 (en) * | 2010-06-29 | 2011-12-29 | Analogic Corporation | Airport/aircraft security |
US20120014567A1 (en) * | 2010-07-13 | 2012-01-19 | Polaris Wireless, Inc. | Wireless Location and Facial/Speaker Recognition System |
US20120019656A1 (en) * | 2010-07-23 | 2012-01-26 | Hon Hai Precision Industry Co., Ltd. | System and method for monitoring subjects of interest |
US20120076367A1 (en) * | 2010-09-24 | 2012-03-29 | Erick Tseng | Auto tagging in geo-social networking system |
US20120126939A1 (en) * | 2010-11-18 | 2012-05-24 | Hyundai Motor Company | System and method for managing entrance and exit using driver face identification within vehicle |
US20120188370A1 (en) * | 2011-01-23 | 2012-07-26 | James Bordonaro | Surveillance systems and methods to monitor, recognize, track objects and unusual activities in real time within user defined boundaries in an area |
US20120330834A1 (en) * | 2011-06-24 | 2012-12-27 | American Express Travel Related Services Company, Inc. | Systems and methods for gesture-based interaction with computer systems |
US8494961B1 (en) * | 2010-10-14 | 2013-07-23 | Jpmorgan Chase Bank, N.A. | Image authentication and security system and method |
US20130332509A1 (en) * | 2012-06-07 | 2013-12-12 | Universal City Studios Llc | Queue management system and method |
US8714439B2 (en) | 2011-08-22 | 2014-05-06 | American Express Travel Related Services Company, Inc. | Methods and systems for contactless payments at a merchant |
US20140192056A1 (en) * | 2013-01-08 | 2014-07-10 | Google Inc. | Displaying dynamic content on a map based on user's location and scheduled task |
US20140195965A1 (en) * | 2013-01-10 | 2014-07-10 | Tyco Safety Products Canada Ltd. | Security system and method with scrolling feeds watchlist |
US20140333777A1 (en) * | 2010-05-13 | 2014-11-13 | Honeywell International Inc. | Surveillance system with direct database server storage |
WO2015006369A1 (en) * | 2013-07-08 | 2015-01-15 | Truestream Kk | Real-time analytics, collaboration, from multiple video sources |
CN104464003A (en) * | 2014-12-04 | 2015-03-25 | 重庆晋才富熙科技有限公司 | Concentration checking method |
CN104464004A (en) * | 2014-12-04 | 2015-03-25 | 重庆晋才富熙科技有限公司 | Electronic signing device |
WO2015025249A3 (en) * | 2013-08-23 | 2015-05-14 | Dor Givon | System for video based subject characterization, categorization, identification, tracking, monitoring and/or presence response |
US9230151B2 (en) * | 2007-05-15 | 2016-01-05 | Samsung Electronics Co., Ltd. | Method, apparatus, and system for searching for image and image-related information using a fingerprint of a captured image |
WO2016018613A1 (en) * | 2014-07-31 | 2016-02-04 | Landis+Gyr Innovations, Inc. | Asset security management system |
WO2016028142A1 (en) * | 2014-08-19 | 2016-02-25 | Ariff Faisal | A system for facilitating the identification and authorisation of travellers |
US9317530B2 (en) | 2011-03-29 | 2016-04-19 | Facebook, Inc. | Face recognition based on spatial and temporal proximity |
CN106169071A (en) * | 2016-07-05 | 2016-11-30 | 厦门理工学院 | A kind of Work attendance method based on dynamic human face and chest card recognition and system |
US9588988B2 (en) | 2013-03-15 | 2017-03-07 | Google Inc. | Visual indicators for temporal context on maps |
US9704020B2 (en) | 2015-06-16 | 2017-07-11 | Microsoft Technology Licensing, Llc | Automatic recognition of entities in media-captured events |
US9866916B1 (en) * | 2016-08-17 | 2018-01-09 | International Business Machines Corporation | Audio content delivery from multi-display device ecosystem |
WO2018075443A1 (en) * | 2016-10-17 | 2018-04-26 | Muppirala Ravikumar | Remote identification of person using combined voice print and facial image recognition |
CN108346191A (en) * | 2018-02-06 | 2018-07-31 | 中国平安人寿保险股份有限公司 | Work attendance method, device, computer equipment and storage medium |
CN108492393A (en) * | 2018-03-16 | 2018-09-04 | 百度在线网络技术(北京)有限公司 | Method and apparatus for registering |
CN108629862A (en) * | 2018-04-16 | 2018-10-09 | 上海呈合信息科技有限公司 | It registers method and device |
US10123360B2 (en) * | 2014-01-22 | 2018-11-06 | Reliance Jio Infocomm Limited | System and method for secure wireless communication |
US10152840B2 (en) | 2016-03-16 | 2018-12-11 | Universal City Studios Llc | Virtual queue system and method |
US20190026794A1 (en) * | 2017-07-19 | 2019-01-24 | Toshiba Tec Kabushiki Kaisha | Server apparatus |
CN109271547A (en) * | 2018-07-19 | 2019-01-25 | 国政通科技有限公司 | A kind of tourist's technique for delineating, device and system based on scenic spot real name |
US10276007B2 (en) * | 2015-08-27 | 2019-04-30 | Panasonic Intellectual Property Management Co., Ltd. | Security system and method for displaying images of people |
WO2019084133A1 (en) * | 2017-10-25 | 2019-05-02 | Sensormatic Electronics, LLC | Frictionless access control system embodying satellite cameras for facial recognition |
WO2018213594A3 (en) * | 2017-05-19 | 2019-05-09 | Walmart Apollo, Llc | System and method for smart facilities monitoring |
US10296874B1 (en) | 2007-12-17 | 2019-05-21 | American Express Travel Related Services Company, Inc. | System and method for preventing unauthorized access to financial accounts |
RU2692269C2 (en) * | 2017-10-13 | 2019-06-24 | Федеральное Государственное унитарное предприятие Государственный научно-исследовательский институт гражданской авиации (ФГУП ГосНИИ ГА) | Method of determining level of transport safety of rf civil aviation facilities |
CN110276851A (en) * | 2019-04-28 | 2019-09-24 | 国家电投集团黄河上游水电开发有限责任公司 | A kind of method and its inspection device carrying out intelligent patrol detection in photovoltaic plant using unmanned plane |
US10657782B2 (en) | 2017-12-21 | 2020-05-19 | At&T Intellectual Property I, L.P. | Networked premises security |
EP3668089A1 (en) * | 2013-04-19 | 2020-06-17 | James Carey | Video identification and analytical recognition system |
AU2020202221A1 (en) * | 2019-03-29 | 2020-10-22 | Round Pixel Pty Ltd | Privacy preserving visitor recognition and movement pattern analysis based on computer vision |
CN111951424A (en) * | 2020-06-29 | 2020-11-17 | 山东汇佳软件科技股份有限公司 | Intelligent management system for dormitory |
US10943188B2 (en) | 2016-11-09 | 2021-03-09 | Universal City Studios Llc | Virtual queuing techniques |
WO2021050237A1 (en) * | 2019-09-13 | 2021-03-18 | Royal Caribbean Cruises Ltd. | Facial recognition system and methods for identity credentialing and personalized services |
CN112887343A (en) * | 2021-05-06 | 2021-06-01 | 广东电网有限责任公司佛山供电局 | Management system and management method for network big data |
US11039108B2 (en) | 2013-03-15 | 2021-06-15 | James Carey | Video identification and analytical recognition system |
US20210329175A1 (en) * | 2012-07-31 | 2021-10-21 | Nec Corporation | Image processing system, image processing method, and program |
US11176629B2 (en) * | 2018-12-21 | 2021-11-16 | FreightVerify, Inc. | System and method for monitoring logistical locations and transit entities using a canonical model |
US11189164B2 (en) | 2018-04-27 | 2021-11-30 | Cubic Corporation | Modifying operational settings of a traffic signal |
US20210397823A1 (en) * | 2019-09-17 | 2021-12-23 | Verizon Media Inc. | Computerized system and method for adaptive stranger detection |
US11283937B1 (en) * | 2019-08-15 | 2022-03-22 | Ikorongo Technology, LLC | Sharing images based on face matching in a network |
US11348367B2 (en) * | 2018-12-28 | 2022-05-31 | Homeland Patrol Division Security, Llc | System and method of biometric identification and storing and retrieving suspect information |
US20220198827A1 (en) * | 2019-06-25 | 2022-06-23 | Motorola Solutions, Inc. | System and method for saving bandwidth in performing facial recognition |
US11443036B2 (en) * | 2019-07-30 | 2022-09-13 | Hewlett Packard Enterprise Development Lp | Facial recognition based security by a management controller |
US11568333B2 (en) | 2019-06-27 | 2023-01-31 | Universal City Studios Llc | Systems and methods for a smart virtual queue |
US11615663B1 (en) * | 2014-06-17 | 2023-03-28 | Amazon Technologies, Inc. | User authentication system |
US11688202B2 (en) | 2018-04-27 | 2023-06-27 | Honeywell International Inc. | Facial enrollment and recognition system |
US11743431B2 (en) | 2013-03-15 | 2023-08-29 | James Carey | Video identification and analytical recognition system |
US11847589B2 (en) | 2014-08-20 | 2023-12-19 | Universal City Studios Llc | Virtual queuing system and method |
Families Citing this family (327)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6764009B2 (en) | 2001-05-30 | 2004-07-20 | Lightwaves Systems, Inc. | Method for tagged bar code data interchange |
US7070103B2 (en) * | 2000-01-03 | 2006-07-04 | Tripletail Ventures, Inc. | Method and apparatus for bar code data interchange |
US7798417B2 (en) | 2000-01-03 | 2010-09-21 | Snyder David M | Method for data interchange |
US7942328B2 (en) * | 2000-01-03 | 2011-05-17 | Roelesis Wireless Llc | Method for data interchange |
US7150400B2 (en) * | 2004-05-18 | 2006-12-19 | Tripletail Ventures, Inc. | Method and apparatus for capturing and decoding an image of a remotely located bar code |
US20040148518A1 (en) * | 2003-01-27 | 2004-07-29 | John Grundback | Distributed surveillance system |
US20050084139A1 (en) * | 2003-05-13 | 2005-04-21 | Biocom, Llc | Identity verification system with interoperable and interchangeable input devices |
US20050110634A1 (en) * | 2003-11-20 | 2005-05-26 | Salcedo David M. | Portable security platform |
US7697026B2 (en) * | 2004-03-16 | 2010-04-13 | 3Vr Security, Inc. | Pipeline architecture for analyzing multiple video streams |
US7664183B2 (en) * | 2004-03-16 | 2010-02-16 | 3Vr Security, Inc. | Correlation processing among multiple analyzers of video streams at stages of a pipeline architecture |
US7667732B1 (en) | 2004-03-16 | 2010-02-23 | 3Vr Security, Inc. | Event generation and camera cluster analysis of multiple video streams in a pipeline architecture |
US7663661B2 (en) * | 2004-03-16 | 2010-02-16 | 3Vr Security, Inc. | Feed-customized processing of multiple video streams in a pipeline architecture |
US7840984B1 (en) | 2004-03-17 | 2010-11-23 | Embarq Holdings Company, Llc | Media administering system and method |
US20100033572A1 (en) * | 2004-03-24 | 2010-02-11 | Richard Steven Trela | Ticket-holder security checkpoint system for deterring terrorist attacks |
US7515738B1 (en) * | 2004-08-06 | 2009-04-07 | The United States Of America As Represented By The Secretary Of The Navy | Biometric data collection and storage system |
US7786891B2 (en) * | 2004-08-27 | 2010-08-31 | Embarq Holdings Company, Llc | System and method for an interactive security system for a home |
US7956890B2 (en) * | 2004-09-17 | 2011-06-07 | Proximex Corporation | Adaptive multi-modal integrated biometric identification detection and surveillance systems |
US7840982B1 (en) | 2004-09-28 | 2010-11-23 | Embarq Holding Company, Llc | Video-all call system and method for a facility |
SG121906A1 (en) * | 2004-10-11 | 2006-05-26 | Stratech Systems Ltd | Intelligent vehicle access control system |
US20060190419A1 (en) * | 2005-02-22 | 2006-08-24 | Bunn Frank E | Video surveillance data analysis algorithms, with local and network-shared communications for facial, physical condition, and intoxication recognition, fuzzy logic intelligent camera system |
US8205796B2 (en) * | 2005-03-08 | 2012-06-26 | Cubic Corporation | Transit security detection system |
US8720775B2 (en) | 2005-03-08 | 2014-05-13 | Cubic Corporation | Automatic integrated sensing and access control |
US7765573B1 (en) | 2005-03-08 | 2010-07-27 | Embarq Holdings Company, LLP | IP-based scheduling and control of digital video content delivery |
US7769207B2 (en) * | 2005-04-01 | 2010-08-03 | Olivo Jr John W | System and method for collection, storage, and analysis of biometric data |
US8370639B2 (en) * | 2005-06-16 | 2013-02-05 | Sensible Vision, Inc. | System and method for providing secure access to an electronic device using continuous facial biometrics |
JP2007052770A (en) * | 2005-07-21 | 2007-03-01 | Omron Corp | Monitoring apparatus |
US7880767B2 (en) * | 2005-08-22 | 2011-02-01 | Andrew Chinigo | Security system for mass transit and mass transportation |
WO2007045051A1 (en) | 2005-10-21 | 2007-04-26 | Honeywell Limited | An authorisation system and a method of authorisation |
US8326775B2 (en) * | 2005-10-26 | 2012-12-04 | Cortica Ltd. | Signature generation for multimedia deep-content-classification by a large-scale matching system and method thereof |
US8818916B2 (en) | 2005-10-26 | 2014-08-26 | Cortica, Ltd. | System and method for linking multimedia data elements to web pages |
US10614626B2 (en) | 2005-10-26 | 2020-04-07 | Cortica Ltd. | System and method for providing augmented reality challenges |
US10387914B2 (en) | 2005-10-26 | 2019-08-20 | Cortica, Ltd. | Method for identification of multimedia content elements and adding advertising content respective thereof |
US11403336B2 (en) | 2005-10-26 | 2022-08-02 | Cortica Ltd. | System and method for removing contextually identical multimedia content elements |
US10380267B2 (en) | 2005-10-26 | 2019-08-13 | Cortica, Ltd. | System and method for tagging multimedia content elements |
US9646005B2 (en) | 2005-10-26 | 2017-05-09 | Cortica, Ltd. | System and method for creating a database of multimedia content elements assigned to users |
US10193990B2 (en) | 2005-10-26 | 2019-01-29 | Cortica Ltd. | System and method for creating user profiles based on multimedia content |
US11032017B2 (en) | 2005-10-26 | 2021-06-08 | Cortica, Ltd. | System and method for identifying the context of multimedia content elements |
US10621988B2 (en) | 2005-10-26 | 2020-04-14 | Cortica Ltd | System and method for speech to text translation using cores of a natural liquid architecture system |
US9372940B2 (en) | 2005-10-26 | 2016-06-21 | Cortica, Ltd. | Apparatus and method for determining user attention using a deep-content-classification (DCC) system |
US11019161B2 (en) | 2005-10-26 | 2021-05-25 | Cortica, Ltd. | System and method for profiling users interest based on multimedia content analysis |
US10776585B2 (en) | 2005-10-26 | 2020-09-15 | Cortica, Ltd. | System and method for recognizing characters in multimedia content |
US11216498B2 (en) | 2005-10-26 | 2022-01-04 | Cortica, Ltd. | System and method for generating signatures to three-dimensional multimedia data elements |
US10607355B2 (en) | 2005-10-26 | 2020-03-31 | Cortica, Ltd. | Method and system for determining the dimensions of an object shown in a multimedia content item |
US10691642B2 (en) | 2005-10-26 | 2020-06-23 | Cortica Ltd | System and method for enriching a concept database with homogenous concepts |
US10180942B2 (en) | 2005-10-26 | 2019-01-15 | Cortica Ltd. | System and method for generation of concept structures based on sub-concepts |
US11003706B2 (en) | 2005-10-26 | 2021-05-11 | Cortica Ltd | System and methods for determining access permissions on personalized clusters of multimedia content elements |
US10742340B2 (en) | 2005-10-26 | 2020-08-11 | Cortica Ltd. | System and method for identifying the context of multimedia content elements displayed in a web-page and providing contextual filters respective thereto |
US11604847B2 (en) | 2005-10-26 | 2023-03-14 | Cortica Ltd. | System and method for overlaying content on a multimedia content element based on user interest |
US20160321253A1 (en) | 2005-10-26 | 2016-11-03 | Cortica, Ltd. | System and method for providing recommendations based on user profiles |
US10848590B2 (en) | 2005-10-26 | 2020-11-24 | Cortica Ltd | System and method for determining a contextual insight and providing recommendations based thereon |
US9384196B2 (en) | 2005-10-26 | 2016-07-05 | Cortica, Ltd. | Signature generation for multimedia deep-content-classification by a large-scale matching system and method thereof |
US10380623B2 (en) | 2005-10-26 | 2019-08-13 | Cortica, Ltd. | System and method for generating an advertisement effectiveness performance score |
US10372746B2 (en) | 2005-10-26 | 2019-08-06 | Cortica, Ltd. | System and method for searching applications using multimedia content elements |
US20170262438A1 (en) * | 2005-10-26 | 2017-09-14 | Cortica, Ltd. | System and method for determining analytics based on multimedia content elements |
US10585934B2 (en) | 2005-10-26 | 2020-03-10 | Cortica Ltd. | Method and system for populating a concept database with respect to user identifiers |
US10878646B2 (en) | 2005-12-08 | 2020-12-29 | Smartdrive Systems, Inc. | Vehicle event recorder systems |
US20070153091A1 (en) * | 2005-12-29 | 2007-07-05 | John Watlington | Methods and apparatus for providing privacy in a communication system |
IL173210A0 (en) * | 2006-01-17 | 2007-03-08 | Rafael Advanced Defense Sys | Biometric facial surveillance system |
JP4442571B2 (en) * | 2006-02-10 | 2010-03-31 | ソニー株式会社 | Imaging apparatus and control method thereof |
JP2007241377A (en) * | 2006-03-06 | 2007-09-20 | Sony Corp | Retrieval system, imaging apparatus, data storage device, information processor, picked-up image processing method, information processing method, and program |
JP4525618B2 (en) | 2006-03-06 | 2010-08-18 | ソニー株式会社 | Video surveillance system and video surveillance program |
US7705731B2 (en) * | 2006-03-10 | 2010-04-27 | Morpho Detection, Inc. | Verification and screening system |
US7868758B2 (en) * | 2006-03-10 | 2011-01-11 | Morpho Detection, Inc. | Passenger screening system and method |
US8996240B2 (en) | 2006-03-16 | 2015-03-31 | Smartdrive Systems, Inc. | Vehicle event recorders with integrated web server |
US20070252001A1 (en) * | 2006-04-25 | 2007-11-01 | Kail Kevin J | Access control system with RFID and biometric facial recognition |
US20070257986A1 (en) * | 2006-05-05 | 2007-11-08 | Ivanov Yuri A | Method for processing queries for surveillance tasks |
JP4751776B2 (en) * | 2006-06-19 | 2011-08-17 | オリンパスイメージング株式会社 | Electronic imaging device and personal identification system |
US20080074496A1 (en) * | 2006-09-22 | 2008-03-27 | Object Video, Inc. | Video analytics for banking business process monitoring |
US7881505B2 (en) * | 2006-09-29 | 2011-02-01 | Pittsburgh Pattern Recognition, Inc. | Video retrieval system for human face content |
US10733326B2 (en) | 2006-10-26 | 2020-08-04 | Cortica Ltd. | System and method for identification of inappropriate multimedia content |
US8989959B2 (en) | 2006-11-07 | 2015-03-24 | Smartdrive Systems, Inc. | Vehicle operator performance history recording, scoring and reporting systems |
US8649933B2 (en) | 2006-11-07 | 2014-02-11 | Smartdrive Systems Inc. | Power management systems for automotive video event recorders |
CA2669269A1 (en) * | 2006-11-08 | 2008-05-15 | Cryptometrics, Inc. | System and method for parallel image processing |
US8868288B2 (en) | 2006-11-09 | 2014-10-21 | Smartdrive Systems, Inc. | Vehicle exception event management systems |
US7751597B2 (en) * | 2006-11-14 | 2010-07-06 | Lctank Llc | Apparatus and method for identifying a name corresponding to a face or voice using a database |
US7986230B2 (en) * | 2006-11-14 | 2011-07-26 | TrackThings LLC | Apparatus and method for finding a misplaced object using a database and instructions generated by a portable device |
KR100796044B1 (en) * | 2007-02-08 | 2008-01-21 | (주)올라웍스 | Method for tagging a person image |
JP5158671B2 (en) * | 2007-02-16 | 2013-03-06 | 株式会社ユニバーサルエンターテインメント | Sand equipment |
US20080201327A1 (en) * | 2007-02-20 | 2008-08-21 | Ashoke Seth | Identity match process |
US7777783B1 (en) | 2007-03-23 | 2010-08-17 | Proximex Corporation | Multi-video navigation |
US9544563B1 (en) | 2007-03-23 | 2017-01-10 | Proximex Corporation | Multi-video navigation system |
US7926705B2 (en) * | 2007-04-20 | 2011-04-19 | Morpho Detection, Inc. | Method and system for using a recording device in an inspection system |
ITAV20070003U1 (en) * | 2007-09-14 | 2007-12-14 | Silvio Spiniello | UTILITY MODEL FROM THE "SECUTITY" NAME FOR PREVENTION, REPRESSION, SAFETY, THE SEARCH FOR MISSING PEOPLE AND THE HISTORICAL REBUILDING OF ACTUALLY FACTED FACTS. |
US8660299B2 (en) * | 2007-09-22 | 2014-02-25 | Honeywell International Inc. | Automated person identification and location for search applications |
KR101319544B1 (en) * | 2007-10-25 | 2013-10-21 | 삼성전자주식회사 | Photographing apparatus for detecting appearance of person and method thereof |
US8131750B2 (en) * | 2007-12-28 | 2012-03-06 | Microsoft Corporation | Real-time annotator |
EP2075400B1 (en) * | 2007-12-31 | 2012-08-08 | March Networks S.p.A. | Video monitoring system |
DE112009000485T5 (en) * | 2008-03-03 | 2011-03-17 | VideoIQ, Inc., Bedford | Object comparison for tracking, indexing and searching |
KR101618735B1 (en) * | 2008-04-02 | 2016-05-09 | 구글 인코포레이티드 | Method and apparatus to incorporate automatic face recognition in digital image collections |
EP2112806B1 (en) * | 2008-04-14 | 2013-03-20 | Axis AB | Information collecting system |
US8237551B2 (en) * | 2008-04-30 | 2012-08-07 | Centurylink Intellectual Property Llc | System and method for in-patient telephony |
US8006291B2 (en) | 2008-05-13 | 2011-08-23 | Veritrix, Inc. | Multi-channel multi-factor authentication |
US8516562B2 (en) | 2008-05-13 | 2013-08-20 | Veritrix, Inc. | Multi-channel multi-factor authentication |
US8536976B2 (en) * | 2008-06-11 | 2013-09-17 | Veritrix, Inc. | Single-channel multi-factor authentication |
US8468358B2 (en) * | 2010-11-09 | 2013-06-18 | Veritrix, Inc. | Methods for identifying the guarantor of an application |
CN103402070B (en) | 2008-05-19 | 2017-07-07 | 日立麦克赛尔株式会社 | Record reproducing device and method |
JP5733775B2 (en) * | 2008-06-06 | 2015-06-10 | 日本電気株式会社 | Object image display system |
US8600121B2 (en) * | 2008-07-02 | 2013-12-03 | C-True Ltd. | Face recognition system and method |
US8166297B2 (en) | 2008-07-02 | 2012-04-24 | Veritrix, Inc. | Systems and methods for controlling access to encrypted data stored on a mobile device |
US10929651B2 (en) | 2008-07-21 | 2021-02-23 | Facefirst, Inc. | Biometric notification system |
US9405968B2 (en) * | 2008-07-21 | 2016-08-02 | Facefirst, Inc | Managed notification system |
US10043060B2 (en) | 2008-07-21 | 2018-08-07 | Facefirst, Inc. | Biometric notification system |
US9141863B2 (en) * | 2008-07-21 | 2015-09-22 | Facefirst, Llc | Managed biometric-based notification system and method |
US10909400B2 (en) | 2008-07-21 | 2021-02-02 | Facefirst, Inc. | Managed notification system |
US9721167B2 (en) * | 2008-07-21 | 2017-08-01 | Facefirst, Inc. | Biometric notification system |
DE102008041933A1 (en) * | 2008-09-10 | 2010-03-11 | Robert Bosch Gmbh | Monitoring system, method for detecting and / or tracking a surveillance object and computer programs |
JP2010081480A (en) * | 2008-09-29 | 2010-04-08 | Fujifilm Corp | Portable suspicious individual detecting apparatus, suspicious individual detecting method, and program |
US9123223B1 (en) | 2008-10-13 | 2015-09-01 | Target Brands, Inc. | Video monitoring system using an alarm sensor for an exit facilitating access to captured video |
WO2010051342A1 (en) | 2008-11-03 | 2010-05-06 | Veritrix, Inc. | User authentication for social networks |
JP2010117487A (en) * | 2008-11-12 | 2010-05-27 | Fujinon Corp | Autofocus system |
JP5289022B2 (en) * | 2008-12-11 | 2013-09-11 | キヤノン株式会社 | Information processing apparatus and information processing method |
US8913488B2 (en) | 2008-12-23 | 2014-12-16 | Bce Inc. | Methods and systems for enabling end-user equipment at an end-user premise to effect communications having certain origins when an ability of the end-user equipment to communicate via a communication link connecting the end-user equipment to a communications network is disrupted |
US9049576B2 (en) * | 2008-12-23 | 2015-06-02 | Bce Inc. | Methods and systems for enabling end-user equipment at an end-user premise to effect communications having certain destinations when an ability of the end-user equipment to communicate via a communication link connecting the end-user equipment to a communications network is disrupted |
CA2748266C (en) | 2008-12-23 | 2017-11-14 | Jonathan Allan Arsenault | Methods and systems for enabling end-user equipment at an end-user premise to effect communications when an ability of the end-user equipment to communicate via a communication link connecting the end-user equipment to a communications network is disrupted |
US9875642B2 (en) | 2008-12-24 | 2018-01-23 | Bce Inc. | Methods and systems for notifying a party at an end-user premise when a particular event occurs at another end-user premise |
US20100164680A1 (en) * | 2008-12-31 | 2010-07-01 | L3 Communications Integrated Systems, L.P. | System and method for identifying people |
TWI427541B (en) * | 2009-03-18 | 2014-02-21 | Ind Tech Res Inst | System and method for performing rapid facial recognition |
US20100237984A1 (en) * | 2009-03-19 | 2010-09-23 | Christopher Zenaty | Apparatus and Methods for Providing Access Control and Video Surveillance at Access Control Points |
WO2010106474A1 (en) | 2009-03-19 | 2010-09-23 | Honeywell International Inc. | Systems and methods for managing access control devices |
EP2452489B1 (en) * | 2009-07-08 | 2020-06-17 | Honeywell International Inc. | Systems and methods for managing video data |
US8379917B2 (en) * | 2009-10-02 | 2013-02-19 | DigitalOptics Corporation Europe Limited | Face recognition performance using additional image features |
US8531523B2 (en) * | 2009-12-08 | 2013-09-10 | Trueposition, Inc. | Multi-sensor location and identification |
US9280365B2 (en) | 2009-12-17 | 2016-03-08 | Honeywell International Inc. | Systems and methods for managing configuration data at disconnected remote devices |
US20110150296A1 (en) * | 2009-12-23 | 2011-06-23 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110150297A1 (en) * | 2009-12-23 | 2011-06-23 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110150276A1 (en) * | 2009-12-23 | 2011-06-23 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110150298A1 (en) * | 2009-12-23 | 2011-06-23 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US8712110B2 (en) * | 2009-12-23 | 2014-04-29 | The Invention Science Fund I, LC | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110150299A1 (en) * | 2009-12-23 | 2011-06-23 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110150295A1 (en) * | 2009-12-23 | 2011-06-23 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110211739A1 (en) * | 2009-12-23 | 2011-09-01 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US9875719B2 (en) * | 2009-12-23 | 2018-01-23 | Gearbox, Llc | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20110211738A1 (en) * | 2009-12-23 | 2011-09-01 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
FR2954846B1 (en) * | 2009-12-30 | 2012-07-13 | Thales Sa | GENERIC THREAT DETECTOR |
US8559669B2 (en) | 2010-03-01 | 2013-10-15 | Cubic Corporation | Security polymer threat detection distribution system |
US20130011014A1 (en) * | 2010-03-09 | 2013-01-10 | Jesse Sheng Jin | Surveillance system and method |
US20120007975A1 (en) * | 2010-06-01 | 2012-01-12 | Lyons Nicholas P | Processing image data |
EP2397995B1 (en) * | 2010-06-21 | 2014-08-20 | Eldon Technology Limited | Anti fare evasion system |
US20120023412A1 (en) * | 2010-07-26 | 2012-01-26 | Alcatel-Lucent Usa Inc. | System and Method for Providing Multimedia Content During an Event |
FR2963093B1 (en) * | 2010-07-26 | 2012-08-03 | Vit | INSTALLATION OF 3D OPTICAL INSPECTION OF ELECTRONIC CIRCUITS |
FR2963144B1 (en) * | 2010-07-26 | 2012-12-07 | Vit | OPTICAL INSPECTION INSTALLATION OF ELECTRONIC CIRCUITS |
WO2012023930A1 (en) * | 2010-08-17 | 2012-02-23 | Empire Technology Development Llc | Remote display control |
US10477158B2 (en) | 2010-11-05 | 2019-11-12 | Razberi Technologies, Inc. | System and method for a security system |
US10157526B2 (en) | 2010-11-05 | 2018-12-18 | Razberi Technologies, Inc. | System and method for a security system |
US11082665B2 (en) | 2010-11-05 | 2021-08-03 | Razberi Secure Technologies, Llc | System and method for a security system |
US9860490B2 (en) | 2010-11-05 | 2018-01-02 | Tom Galvin | Network video recorder system |
US8922658B2 (en) | 2010-11-05 | 2014-12-30 | Tom Galvin | Network video recorder system |
US8787725B2 (en) | 2010-11-11 | 2014-07-22 | Honeywell International Inc. | Systems and methods for managing video data |
US8700644B1 (en) * | 2010-12-13 | 2014-04-15 | Sure To Meet, LLC | Computerized matching and introduction systems and methods |
JP5617627B2 (en) * | 2010-12-28 | 2014-11-05 | オムロン株式会社 | Monitoring device and method, and program |
WO2012102828A1 (en) * | 2011-01-25 | 2012-08-02 | Searete Llc | Identifying a characteristic of an individual utilizing facial recognition and providing a display for the individual |
US20120307070A1 (en) * | 2011-06-02 | 2012-12-06 | James Pierce | Surveillance method utilizing video compression for wireless transmission |
EP2718895A4 (en) * | 2011-06-06 | 2014-11-05 | Stoplift Inc | Notification system and methods for use in retail environments |
US8942990B2 (en) | 2011-06-06 | 2015-01-27 | Next Level Security Systems, Inc. | Return fraud protection system |
US9552376B2 (en) | 2011-06-09 | 2017-01-24 | MemoryWeb, LLC | Method and apparatus for managing digital files |
US8705812B2 (en) | 2011-06-10 | 2014-04-22 | Amazon Technologies, Inc. | Enhanced face recognition in video |
WO2012174603A1 (en) | 2011-06-24 | 2012-12-27 | Honeywell International Inc. | Systems and methods for presenting dvm system information |
US8396877B2 (en) | 2011-06-27 | 2013-03-12 | Raytheon Company | Method and apparatus for generating a fused view of one or more people |
WO2013020165A2 (en) | 2011-08-05 | 2013-02-14 | HONEYWELL INTERNATIONAL INC. Attn: Patent Services | Systems and methods for managing video data |
US10362273B2 (en) | 2011-08-05 | 2019-07-23 | Honeywell International Inc. | Systems and methods for managing video data |
US9344684B2 (en) | 2011-08-05 | 2016-05-17 | Honeywell International Inc. | Systems and methods configured to enable content sharing between client terminals of a digital video management system |
US8474014B2 (en) | 2011-08-16 | 2013-06-25 | Veritrix, Inc. | Methods for the secure use of one-time passwords |
JP5216126B2 (en) * | 2011-08-19 | 2013-06-19 | 三菱重工業株式会社 | Dangerous substance detection system |
US9288513B2 (en) | 2011-08-29 | 2016-03-15 | Aerovironment, Inc. | System and method of high-resolution digital data image transmission |
US11401045B2 (en) | 2011-08-29 | 2022-08-02 | Aerovironment, Inc. | Camera ball turret having high bandwidth data transmission to external image processor |
US20130057693A1 (en) * | 2011-09-02 | 2013-03-07 | John Baranek | Intruder imaging and identification system |
US9269243B2 (en) * | 2011-10-07 | 2016-02-23 | Siemens Aktiengesellschaft | Method and user interface for forensic video search |
US20130145293A1 (en) * | 2011-12-01 | 2013-06-06 | Avaya Inc. | Methods, apparatuses, and computer-readable media for providing availability metaphor(s) representing communications availability in an interactive map |
US9519769B2 (en) * | 2012-01-09 | 2016-12-13 | Sensible Vision, Inc. | System and method for disabling secure access to an electronic device using detection of a predetermined device orientation |
GB2499449A (en) * | 2012-02-20 | 2013-08-21 | Taiwan Colour And Imaging Technology Corp | Surveillance by face recognition using colour display of images |
FR2987474A1 (en) * | 2012-02-24 | 2013-08-30 | Jacques Salmon | METHOD FOR AUTHENTICATING THE HOLDER OF A CHIP CARD |
US9355107B2 (en) * | 2012-04-20 | 2016-05-31 | 3Rd Forensic Limited | Crime investigation system |
US9728228B2 (en) | 2012-08-10 | 2017-08-08 | Smartdrive Systems, Inc. | Vehicle event playback apparatus and methods |
EP2704052A1 (en) * | 2012-08-28 | 2014-03-05 | Solink Corporation | Transaction verification system |
CN102968827A (en) * | 2012-11-22 | 2013-03-13 | 成都江法科技有限公司 | Human face identification security and protection attendance system based on cloud data processing bank |
TWI493432B (en) * | 2012-11-22 | 2015-07-21 | Mstar Semiconductor Inc | User interface generating apparatus and associated method |
CN102968828A (en) * | 2012-11-22 | 2013-03-13 | 成都江法科技有限公司 | Face recognition security and protection attendance system |
CN103916626A (en) * | 2013-01-05 | 2014-07-09 | 中兴通讯股份有限公司 | Monitoring video information providing method and device and video monitoring system |
US8824751B2 (en) * | 2013-01-07 | 2014-09-02 | MTN Satellite Communications | Digital photograph group editing and access |
US8874471B2 (en) * | 2013-01-29 | 2014-10-28 | Wal-Mart Stores, Inc. | Retail loss prevention using biometric data |
US9398283B2 (en) | 2013-02-12 | 2016-07-19 | Honeywell International Inc. | System and method of alarm and history video playback |
JP6080940B2 (en) * | 2013-02-28 | 2017-02-15 | 株式会社日立国際電気 | Person search method and home staying person search device |
US20140278629A1 (en) * | 2013-03-12 | 2014-09-18 | PayrollHero.com Pte. Ltd. | Method for employee parameter tracking |
US9143938B2 (en) | 2013-03-15 | 2015-09-22 | Tyfone, Inc. | Personal digital identity device responsive to user interaction |
US9436165B2 (en) | 2013-03-15 | 2016-09-06 | Tyfone, Inc. | Personal digital identity device with motion sensor responsive to user interaction |
US9215592B2 (en) | 2013-03-15 | 2015-12-15 | Tyfone, Inc. | Configurable personal digital identity device responsive to user interaction |
US9319881B2 (en) | 2013-03-15 | 2016-04-19 | Tyfone, Inc. | Personal digital identity device with fingerprint sensor |
US9183371B2 (en) | 2013-03-15 | 2015-11-10 | Tyfone, Inc. | Personal digital identity device with microphone |
US9231945B2 (en) | 2013-03-15 | 2016-01-05 | Tyfone, Inc. | Personal digital identity device with motion sensor |
US9086689B2 (en) | 2013-03-15 | 2015-07-21 | Tyfone, Inc. | Configurable personal digital identity device with imager responsive to user interaction |
US9154500B2 (en) | 2013-03-15 | 2015-10-06 | Tyfone, Inc. | Personal digital identity device with microphone responsive to user interaction |
US9762865B2 (en) * | 2013-03-15 | 2017-09-12 | James Carey | Video identification and analytical recognition system |
US20140270175A1 (en) * | 2013-03-15 | 2014-09-18 | Tyfone, Inc. | Personal digital identity device with imager |
US9781598B2 (en) | 2013-03-15 | 2017-10-03 | Tyfone, Inc. | Personal digital identity device with fingerprint sensor responsive to user interaction |
US9207650B2 (en) | 2013-03-15 | 2015-12-08 | Tyfone, Inc. | Configurable personal digital identity device responsive to user interaction with user authentication factor captured in mobile device |
US9448543B2 (en) | 2013-03-15 | 2016-09-20 | Tyfone, Inc. | Configurable personal digital identity device with motion sensor responsive to user interaction |
WO2014148395A1 (en) * | 2013-03-21 | 2014-09-25 | 株式会社日立国際電気 | Video monitoring system, video monitoring method, and video monitoring device |
CN103279740B (en) * | 2013-05-15 | 2016-06-29 | 吴玉平 | A kind of method and system utilizing dynamic data base to accelerate intelligent monitoring recognition of face |
EP3005639B1 (en) * | 2013-06-04 | 2017-08-09 | Smiley Owl Tech S.L. | Method and system for verifying the identity of a user of an online service |
JP6358258B2 (en) * | 2013-09-19 | 2018-07-18 | 日本電気株式会社 | Image processing system, image processing method, and program |
US9501878B2 (en) | 2013-10-16 | 2016-11-22 | Smartdrive Systems, Inc. | Vehicle event playback apparatus and methods |
US10523903B2 (en) | 2013-10-30 | 2019-12-31 | Honeywell International Inc. | Computer implemented systems frameworks and methods configured for enabling review of incident data |
US9610955B2 (en) | 2013-11-11 | 2017-04-04 | Smartdrive Systems, Inc. | Vehicle fuel consumption monitor and feedback systems |
US20150142587A1 (en) * | 2013-11-20 | 2015-05-21 | Honeywell International Inc. | System and Method of Dynamic Correlation View for Cloud Based Incident Analysis and Pattern Detection |
US10510054B1 (en) | 2013-12-30 | 2019-12-17 | Wells Fargo Bank, N.A. | Augmented reality enhancements for financial activities |
AU2014373892A1 (en) * | 2014-01-03 | 2016-06-30 | Gleim Conferencing, Llc | System and method for validating test takers |
US9792594B1 (en) | 2014-01-10 | 2017-10-17 | Wells Fargo Bank, N.A. | Augmented reality security applications |
US10078867B1 (en) | 2014-01-10 | 2018-09-18 | Wells Fargo Bank, N.A. | Augmented reality virtual banker |
US11276062B1 (en) | 2014-01-10 | 2022-03-15 | Wells Fargo Bank, N.A. | Augmented reality security applications |
US20160350583A1 (en) * | 2014-01-23 | 2016-12-01 | Hitachi Kokusai Electric Inc. | Image search system and image search method |
GB201402856D0 (en) * | 2014-02-18 | 2014-04-02 | Right Track Recruitment Uk Ltd | System and method for recordal of personnel attendance |
US8892310B1 (en) | 2014-02-21 | 2014-11-18 | Smartdrive Systems, Inc. | System and method to detect execution of driving maneuvers |
US9344419B2 (en) | 2014-02-27 | 2016-05-17 | K.Y. Trix Ltd. | Methods of authenticating users to a site |
US20150269692A1 (en) * | 2014-03-18 | 2015-09-24 | Jed Ryan | Electronic Contract Creator |
US20150278977A1 (en) * | 2015-03-25 | 2015-10-01 | Digital Signal Corporation | System and Method for Detecting Potential Fraud Between a Probe Biometric and a Dataset of Biometrics |
US9269159B2 (en) | 2014-06-05 | 2016-02-23 | Promethean Limited | Systems and methods for tracking object association over time |
US9524418B2 (en) | 2014-06-05 | 2016-12-20 | Promethean Limited | Systems and methods for detecting, identifying and tracking objects and events over time |
US9398213B1 (en) | 2014-07-11 | 2016-07-19 | ProSports Technologies, LLC | Smart field goal detector |
US9724588B1 (en) | 2014-07-11 | 2017-08-08 | ProSports Technologies, LLC | Player hit system |
WO2016007970A1 (en) | 2014-07-11 | 2016-01-14 | ProSports Technologies, LLC | Whistle play stopper |
US9474933B1 (en) | 2014-07-11 | 2016-10-25 | ProSports Technologies, LLC | Professional workout simulator |
US9610491B2 (en) | 2014-07-11 | 2017-04-04 | ProSports Technologies, LLC | Playbook processor |
US9305441B1 (en) | 2014-07-11 | 2016-04-05 | ProSports Technologies, LLC | Sensor experience shirt |
US10264175B2 (en) | 2014-09-09 | 2019-04-16 | ProSports Technologies, LLC | Facial recognition for event venue cameras |
AU2015224526B2 (en) * | 2014-09-11 | 2020-04-30 | Iomniscient Pty Ltd | An image management system |
CN112904880A (en) * | 2014-10-31 | 2021-06-04 | 深圳市大疆创新科技有限公司 | System and method for monitoring with visual indicia |
US11069257B2 (en) | 2014-11-13 | 2021-07-20 | Smartdrive Systems, Inc. | System and method for detecting a vehicle event and generating review criteria |
CA2966553A1 (en) * | 2014-12-04 | 2016-06-09 | Cubic Corporation | Credit and debit fraud card usage monitoring for transit |
WO2016093553A1 (en) * | 2014-12-12 | 2016-06-16 | 서울대학교 산학협력단 | System for collecting event data, method for collecting event data, service server for collecting event data, and camera |
FR3031825B1 (en) * | 2015-01-19 | 2018-03-09 | Rizze | METHOD FOR FACIAL RECOGNITION AND INDEXING OF RECOGNIZED PERSONS IN A VIDEO STREAM |
CN104616364B (en) * | 2015-01-28 | 2017-02-22 | 福建亿榕信息技术有限公司 | Method and system for remote attendance checking of enterprise staffs based on face identification |
WO2016126729A1 (en) * | 2015-02-03 | 2016-08-11 | Visa International Service Association | Validation identity tokens for transactions |
US10091464B2 (en) * | 2015-02-13 | 2018-10-02 | 355323 B.C. Ltd. | Image/location-based tracking |
CN105518713A (en) * | 2015-02-15 | 2016-04-20 | 北京旷视科技有限公司 | Living human face verification method and system, computer program product |
US9861281B2 (en) * | 2015-03-19 | 2018-01-09 | Accenture Global Services Limited | Telemetrics and alert system |
US9679420B2 (en) | 2015-04-01 | 2017-06-13 | Smartdrive Systems, Inc. | Vehicle event recording system and method |
CN104834902A (en) * | 2015-04-21 | 2015-08-12 | 同方威视技术股份有限公司 | Safety check graph discrimination system including video analysis and graph discrimination method |
US10146797B2 (en) | 2015-05-29 | 2018-12-04 | Accenture Global Services Limited | Face recognition image data cache |
WO2017033186A1 (en) * | 2015-08-24 | 2017-03-02 | Fst21 Ltd | System and method for in motion identification |
KR102361088B1 (en) * | 2015-11-27 | 2022-02-09 | 한화테크윈 주식회사 | Method of sharing image |
WO2017105641A1 (en) | 2015-12-15 | 2017-06-22 | Cortica, Ltd. | Identification of key points in multimedia data elements |
US11195043B2 (en) | 2015-12-15 | 2021-12-07 | Cortica, Ltd. | System and method for determining common patterns in multimedia content elements based on key points |
US10289966B2 (en) * | 2016-03-01 | 2019-05-14 | Fmr Llc | Dynamic seating and workspace planning |
JP6736340B2 (en) * | 2016-04-19 | 2020-08-05 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
JP6762754B2 (en) * | 2016-04-19 | 2020-09-30 | キヤノン株式会社 | Information processing equipment, information processing methods and programs |
KR102284448B1 (en) * | 2016-04-19 | 2021-08-02 | 캐논 가부시끼가이샤 | Information processing apparatus, information processing method, and storage medium |
EP3246849A1 (en) * | 2016-05-18 | 2017-11-22 | L-1 Identity Solutions AG | Method for analyzing video data |
US10402643B2 (en) * | 2016-06-15 | 2019-09-03 | Google Llc | Object rejection system and method |
CN106127618B (en) * | 2016-06-21 | 2019-12-24 | 深圳中琛源科技股份有限公司 | Positioning monitoring system and method based on face recognition, people number induction and radio frequency identification |
US9996773B2 (en) * | 2016-08-04 | 2018-06-12 | International Business Machines Corporation | Face recognition in big data ecosystem using multiple recognition models |
GB2553123A (en) * | 2016-08-24 | 2018-02-28 | Fujitsu Ltd | Data collector |
US10218855B2 (en) * | 2016-11-14 | 2019-02-26 | Alarm.Com Incorporated | Doorbell call center |
US10297059B2 (en) | 2016-12-21 | 2019-05-21 | Motorola Solutions, Inc. | Method and image processor for sending a combined image to human versus machine consumers |
CN106846527B (en) * | 2017-02-24 | 2019-03-29 | 杭州腾昊科技有限公司 | A kind of attendance checking system based on recognition of face |
WO2018191648A1 (en) | 2017-04-14 | 2018-10-18 | Yang Liu | System and apparatus for co-registration and correlation between multi-modal imagery and method for same |
EP3616095A4 (en) * | 2017-04-28 | 2020-12-30 | Cherry Labs, Inc. | Computer vision based monitoring system and method |
WO2019008581A1 (en) | 2017-07-05 | 2019-01-10 | Cortica Ltd. | Driving policies determination |
WO2019012527A1 (en) | 2017-07-09 | 2019-01-17 | Cortica Ltd. | Deep learning networks orchestration |
US10535145B2 (en) | 2017-07-14 | 2020-01-14 | Motorola Solutions, Inc. | Context-based, partial edge intelligence facial and vocal characteristic recognition |
EP3652673A1 (en) | 2017-08-29 | 2020-05-20 | Siemens Mobility GmbH | Person recognition in areas with limited data transmission and data processing |
EP3699880B1 (en) * | 2017-11-17 | 2021-11-10 | Mitsubishi Electric Corporation | Person display control device, person display control system and person display control method |
US11622092B2 (en) | 2017-12-26 | 2023-04-04 | Pixart Imaging Inc. | Image sensing scheme capable of saving more power as well as avoiding image lost and also simplifying complex image recursive calculation |
US10645351B2 (en) * | 2017-12-26 | 2020-05-05 | Primesensor Technology Inc. | Smart motion detection device and related determining method |
US11405581B2 (en) | 2017-12-26 | 2022-08-02 | Pixart Imaging Inc. | Motion detection methods and image sensor devices capable of generating ranking list of regions of interest and pre-recording monitoring images |
US10499019B2 (en) | 2017-12-26 | 2019-12-03 | Primesensor Technology Inc. | Motion detection device and motion detection method thereof |
CN108182414B (en) | 2017-12-29 | 2021-03-16 | 创新先进技术有限公司 | Traffic detection method, device and system |
CN108090989B (en) * | 2017-12-29 | 2021-08-24 | 长威信息科技发展股份有限公司 | Machine room inspection method and system |
JP6525072B1 (en) | 2018-01-12 | 2019-06-05 | 日本電気株式会社 | Face recognition device |
EP3528169A1 (en) * | 2018-02-15 | 2019-08-21 | Panasonic Intellectual Property Management Co., Ltd. | Image transmission apparatus, camera system, and image transmission method |
CN108345868A (en) * | 2018-03-09 | 2018-07-31 | 广东万峯信息科技有限公司 | Public transport based on face recognition technology is pursued and captured an escaped prisoner system and its control method |
US11735018B2 (en) * | 2018-03-11 | 2023-08-22 | Intellivision Technologies Corp. | Security system with face recognition |
CN110324528A (en) * | 2018-03-28 | 2019-10-11 | 富泰华工业(深圳)有限公司 | Photographic device, image processing system and method |
FR3080938B1 (en) * | 2018-05-03 | 2021-05-07 | Royal Caribbean Cruises Ltd | HIGH-SPEED IDENTIFICATION OF PASSENGERS IN GATE MONITORING |
US10713476B2 (en) * | 2018-05-03 | 2020-07-14 | Royal Caribbean Cruises Ltd. | High throughput passenger identification in portal monitoring |
CN108921034A (en) * | 2018-06-05 | 2018-11-30 | 北京市商汤科技开发有限公司 | Face matching process and device, storage medium |
WO2019245559A2 (en) | 2018-06-21 | 2019-12-26 | Visa International Service Association | System and method for detecting and preventing "friendly fraud" |
US20190392691A1 (en) * | 2018-06-26 | 2019-12-26 | The Chamberlain Group, Inc. | Entry security system and method |
US10837216B2 (en) | 2018-06-26 | 2020-11-17 | The Chamberlain Group, Inc. | Garage entry system and method |
US10846544B2 (en) | 2018-07-16 | 2020-11-24 | Cartica Ai Ltd. | Transportation prediction system and method |
CN110728166A (en) * | 2018-07-16 | 2020-01-24 | 博博熊教育科技(中山)有限公司 | Intelligent monitoring integrated system for confirming track by face recognition |
EP3832587A4 (en) | 2018-07-31 | 2022-02-23 | NEC Corporation | Information processing device, information processing method, and recording medium |
JP7114407B2 (en) * | 2018-08-30 | 2022-08-08 | 株式会社東芝 | Matching system |
GB2577689B (en) | 2018-10-01 | 2023-03-22 | Digital Barriers Services Ltd | Video surveillance and object recognition |
JP7153205B2 (en) * | 2018-10-11 | 2022-10-14 | 日本電気株式会社 | Information processing device, information processing method and program |
WO2020081043A1 (en) * | 2018-10-15 | 2020-04-23 | Visa International Service Association | System, method, and computer program product for processing a chargeback or pre-processing request |
US10839694B2 (en) | 2018-10-18 | 2020-11-17 | Cartica Ai Ltd | Blind spot alert |
US11126870B2 (en) | 2018-10-18 | 2021-09-21 | Cartica Ai Ltd. | Method and system for obstacle detection |
US20200133308A1 (en) | 2018-10-18 | 2020-04-30 | Cartica Ai Ltd | Vehicle to vehicle (v2v) communication less truck platooning |
US11181911B2 (en) | 2018-10-18 | 2021-11-23 | Cartica Ai Ltd | Control transfer of a vehicle |
US11700356B2 (en) | 2018-10-26 | 2023-07-11 | AutoBrains Technologies Ltd. | Control transfer of a vehicle |
US10789535B2 (en) | 2018-11-26 | 2020-09-29 | Cartica Ai Ltd | Detection of road elements |
TWI697775B (en) * | 2018-12-04 | 2020-07-01 | 谷林運算股份有限公司 | Modularization monitoring device |
CN109887114A (en) * | 2018-12-27 | 2019-06-14 | 北京智慧云行科技有限责任公司 | Face batch identification attendance system and method |
US10936178B2 (en) | 2019-01-07 | 2021-03-02 | MemoryWeb, LLC | Systems and methods for analyzing and organizing digital photos and videos |
JP6905553B2 (en) * | 2019-07-03 | 2021-07-21 | パナソニックi−PROセンシングソリューションズ株式会社 | Information processing device, registration method, judgment method, and program |
CN109685043B (en) * | 2019-02-10 | 2020-11-10 | 北京工商大学 | University student classroom state real-time monitoring system based on classroom multimedia device |
US11643005B2 (en) | 2019-02-27 | 2023-05-09 | Autobrains Technologies Ltd | Adjusting adjustable headlights of a vehicle |
US11285963B2 (en) | 2019-03-10 | 2022-03-29 | Cartica Ai Ltd. | Driver-based prediction of dangerous events |
US11694088B2 (en) | 2019-03-13 | 2023-07-04 | Cortica Ltd. | Method for object detection using knowledge distillation |
US11132548B2 (en) | 2019-03-20 | 2021-09-28 | Cortica Ltd. | Determining object information that does not explicitly appear in a media unit signature |
US11488290B2 (en) | 2019-03-31 | 2022-11-01 | Cortica Ltd. | Hybrid representation of a media unit |
US10789527B1 (en) | 2019-03-31 | 2020-09-29 | Cortica Ltd. | Method for object detection using shallow neural networks |
US10776669B1 (en) | 2019-03-31 | 2020-09-15 | Cortica Ltd. | Signature generation and object detection that refer to rare scenes |
US11222069B2 (en) | 2019-03-31 | 2022-01-11 | Cortica Ltd. | Low-power calculation of a signature of a media unit |
US10796444B1 (en) | 2019-03-31 | 2020-10-06 | Cortica Ltd | Configuring spanning elements of a signature generator |
US10789796B1 (en) * | 2019-06-24 | 2020-09-29 | Sufian Munir Inc | Priority-based, facial recognition-assisted attendance determination and validation system |
CN110458303A (en) * | 2019-08-08 | 2019-11-15 | 华北理工大学 | Electrical intelligent fire disaster early warning system |
US11074432B2 (en) * | 2019-08-22 | 2021-07-27 | Nice Ltd. | Systems and methods for retrieving and presenting information using augmented reality |
CN111027471B (en) * | 2019-12-09 | 2024-02-13 | 河南启维智能飞行科技有限公司 | Auxiliary line inspection monitoring management method |
US11593662B2 (en) | 2019-12-12 | 2023-02-28 | Autobrains Technologies Ltd | Unsupervised cluster generation |
US10748022B1 (en) | 2019-12-12 | 2020-08-18 | Cartica Ai Ltd | Crowd separation |
US11403734B2 (en) | 2020-01-07 | 2022-08-02 | Ademco Inc. | Systems and methods for converting low resolution images into high resolution images |
CN111192377B (en) * | 2020-01-08 | 2021-08-27 | 中国银联股份有限公司 | Image processing method and device |
US11321554B2 (en) | 2020-01-30 | 2022-05-03 | Universal City Studios Llc | Efficient management of facial recognition systems and methods in multiple areas |
US11590988B2 (en) | 2020-03-19 | 2023-02-28 | Autobrains Technologies Ltd | Predictive turning assistant |
CN111522046B (en) * | 2020-03-24 | 2023-06-06 | 南京熊猫电子股份有限公司 | 5G and Beidou-based man-vehicle accompanying judgment method |
US11827215B2 (en) | 2020-03-31 | 2023-11-28 | AutoBrains Technologies Ltd. | Method for training a driving related object detector |
US11335112B2 (en) | 2020-04-27 | 2022-05-17 | Adernco Inc. | Systems and methods for identifying a unified entity from a plurality of discrete parts |
US10997423B1 (en) * | 2020-05-27 | 2021-05-04 | Noa, Inc. | Video surveillance system having enhanced video capture |
US11756424B2 (en) | 2020-07-24 | 2023-09-12 | AutoBrains Technologies Ltd. | Parking assist |
US11763595B2 (en) | 2020-08-27 | 2023-09-19 | Sensormatic Electronics, LLC | Method and system for identifying, tracking, and collecting data on a person of interest |
US11710392B2 (en) | 2020-09-11 | 2023-07-25 | IDEMIA National Security Solutions LLC | Targeted video surveillance processing |
US11921831B2 (en) | 2021-03-12 | 2024-03-05 | Intellivision Technologies Corp | Enrollment system with continuous learning and confirmation |
US11706214B2 (en) * | 2021-04-08 | 2023-07-18 | Cisco Technology, Inc. | Continuous multifactor authentication system integration with corporate security systems |
CN113538723B (en) * | 2021-05-31 | 2023-04-18 | 优刻得科技股份有限公司 | Inspection robot and inspection method |
CN113570644B (en) * | 2021-09-27 | 2021-11-30 | 中国民用航空总局第二研究所 | Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium |
WO2024044185A1 (en) * | 2022-08-23 | 2024-02-29 | SparkCognition, Inc. | Face image matching based on feature comparison |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030210139A1 (en) * | 2001-12-03 | 2003-11-13 | Stephen Brooks | Method and system for improved security |
US6853739B2 (en) * | 2002-05-15 | 2005-02-08 | Bio Com, Llc | Identity verification system |
US6940545B1 (en) * | 2000-02-28 | 2005-09-06 | Eastman Kodak Company | Face detecting camera and method |
US7200755B2 (en) * | 2001-05-24 | 2007-04-03 | Larry Hamid | Method and system for providing gated access for a third party to a secure entity or service |
Family Cites Families (118)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4163283A (en) * | 1977-04-11 | 1979-07-31 | Darby Ronald A | Automatic method to identify aircraft types |
US4179695A (en) | 1978-10-02 | 1979-12-18 | International Telephone And Telegraph Corporation | System for identification of aircraft on airport surface pathways |
US4197536A (en) | 1978-10-30 | 1980-04-08 | International Telephone And Telegraph Corporation | Airport surface identification and control system |
US4516125A (en) * | 1982-09-20 | 1985-05-07 | General Signal Corporation | Method and apparatus for monitoring vehicle ground movement in the vicinity of an airport |
US4845629A (en) * | 1985-07-18 | 1989-07-04 | General De Investigacion Y Desarrollo S.A. | Airport surveillance systems |
US4910692A (en) * | 1985-10-09 | 1990-03-20 | Outram John D | Adaptive data logger |
US4831438A (en) * | 1987-02-25 | 1989-05-16 | Household Data Services | Electronic surveillance system |
EP0317630B1 (en) * | 1987-06-09 | 1997-10-15 | KAWASHIMA, Hiroshi | Apparatus for guiding an aircraft on the ground |
JPS6437903A (en) * | 1987-08-01 | 1989-02-08 | Yoshida Kogyo Kk | Production of slide fastener equipped with opening, separating and engaging jig |
US4891650A (en) * | 1988-05-16 | 1990-01-02 | Trackmobile Inc. | Vehicle location system |
US4857912A (en) * | 1988-07-27 | 1989-08-15 | The United States Of America As Represented By The Secretary Of The Navy | Intelligent security assessment system |
SE462698B (en) * | 1988-10-07 | 1990-08-13 | Swedish Airport Technology Han | FAIR LIGHTING FOR AIRPORT |
EP0377229B1 (en) * | 1989-01-05 | 1996-06-26 | Laboratorios Leti, S.A. | Use of specific properties of allergens from animal sources and methods for their isolation |
JP2896930B2 (en) * | 1989-01-16 | 1999-05-31 | コールズ,クリストファー・フランシス | Photo security system |
EP0427499B1 (en) * | 1989-11-07 | 1995-08-02 | Konica Corporation | Belt type image forming unit |
US5085662A (en) * | 1989-11-13 | 1992-02-04 | Scimed Life Systems, Inc. | Atherectomy catheter and related components |
US5027104A (en) * | 1990-02-21 | 1991-06-25 | Reid Donald J | Vehicle security device |
US5091780A (en) * | 1990-05-09 | 1992-02-25 | Carnegie-Mellon University | A trainable security system emthod for the same |
JP2667924B2 (en) | 1990-05-25 | 1997-10-27 | 東芝テスコ 株式会社 | Aircraft docking guidance device |
US5109278A (en) * | 1990-07-06 | 1992-04-28 | Commonwealth Edison Company | Auto freeze frame display for intrusion monitoring system |
US6195609B1 (en) * | 1993-09-07 | 2001-02-27 | Harold Robert Pilley | Method and system for the control and management of an airport |
US5867804A (en) * | 1993-09-07 | 1999-02-02 | Harold R. Pilley | Method and system for the control and management of a three dimensional space envelope |
JPH07115677B2 (en) * | 1990-10-30 | 1995-12-13 | 嘉三 藤本 | Flight information recording method and apparatus for aircraft |
WO1992010387A1 (en) * | 1990-12-11 | 1992-06-25 | Forecourt Security Developments Limited | Vehicle protection system |
NZ240907A (en) * | 1990-12-14 | 1995-01-27 | Ainsworth Tech Inc | Communication system: signal level adjusting interface between distribution and antenna systems |
US5408330A (en) | 1991-03-25 | 1995-04-18 | Crimtec Corporation | Video incident capture system |
US5243530A (en) * | 1991-07-26 | 1993-09-07 | The United States Of America As Represented By The Secretary Of The Navy | Stand alone multiple unit tracking system |
US5375058A (en) | 1991-12-20 | 1994-12-20 | University Of Central Florida | Surface detection system for airports |
US5448243A (en) * | 1991-12-30 | 1995-09-05 | Deutsche Forschungsanstalt Fur Luft- Und Raumfahrt E.V. | System for locating a plurality of objects and obstructions and for detecting and determining the rolling status of moving objects, such as aircraft, ground vehicles, and the like |
US6226031B1 (en) * | 1992-02-19 | 2001-05-01 | Netergy Networks, Inc. | Video communication/monitoring apparatus and method therefor |
GB2267625B (en) * | 1992-05-20 | 1996-08-21 | Northern Telecom Ltd | Video services |
US5218367A (en) * | 1992-06-01 | 1993-06-08 | Trackmobile | Vehicle tracking system |
US5268698A (en) | 1992-07-31 | 1993-12-07 | Smith Sr Louis P | Target acquisition, locating and tracking system |
US5636122A (en) * | 1992-10-16 | 1997-06-03 | Mobile Information Systems, Inc. | Method and apparatus for tracking vehicle location and computer aided dispatch |
US5777580A (en) * | 1992-11-18 | 1998-07-07 | Trimble Navigation Limited | Vehicle location system |
US6675386B1 (en) * | 1996-09-04 | 2004-01-06 | Discovery Communications, Inc. | Apparatus for video access and control over computer network, including image correction |
US5321615A (en) * | 1992-12-10 | 1994-06-14 | Frisbie Marvin E | Zero visibility surface traffic control system |
US5530440A (en) * | 1992-12-15 | 1996-06-25 | Westinghouse Norden Systems, Inc | Airport surface aircraft locator |
US5351194A (en) * | 1993-05-14 | 1994-09-27 | World Wide Notification Systems, Inc. | Apparatus and method for closing flight plans and locating aircraft |
US5508736A (en) * | 1993-05-14 | 1996-04-16 | Cooper; Roger D. | Video signal processing apparatus for producing a composite signal for simultaneous display of data and video information |
US5714948A (en) * | 1993-05-14 | 1998-02-03 | Worldwide Notifications Systems, Inc. | Satellite based aircraft traffic control system |
US5334982A (en) * | 1993-05-27 | 1994-08-02 | Norden Systems, Inc. | Airport surface vehicle identification |
US5917405A (en) * | 1993-06-08 | 1999-06-29 | Joao; Raymond Anthony | Control apparatus and methods for vehicles |
US5983161A (en) | 1993-08-11 | 1999-11-09 | Lemelson; Jerome H. | GPS vehicle collision avoidance warning and control system and method |
US5497149A (en) * | 1993-09-02 | 1996-03-05 | Fast; Ray | Global security system |
US5463595A (en) | 1993-10-13 | 1995-10-31 | Rodhall; Arne | Portable security system for outdoor sites |
US5440337A (en) * | 1993-11-12 | 1995-08-08 | Puritan-Bennett Corporation | Multi-camera closed circuit television system for aircraft |
US5557254A (en) * | 1993-11-16 | 1996-09-17 | Mobile Security Communications, Inc. | Programmable vehicle monitoring and security system having multiple access verification devices |
CA2170737A1 (en) * | 1994-02-07 | 1995-08-10 | Harold Ii Pace | Mobile location reporting apparatus and methods |
US5440343A (en) * | 1994-02-28 | 1995-08-08 | Eastman Kodak Company | Motion/still electronic image sensing apparatus |
US5400031A (en) * | 1994-03-07 | 1995-03-21 | Norden Systems, Inc. | Airport surface vehicle identification system and method |
EP0707704B1 (en) * | 1994-05-06 | 2000-02-09 | Koninklijke Philips Electronics N.V. | A method and apparatus for differential location of a vehicle under control of an internal change of status |
US5777551A (en) * | 1994-09-09 | 1998-07-07 | Hess; Brian K. | Portable alarm system |
US5850180A (en) | 1994-09-09 | 1998-12-15 | Tattletale Portable Alarm Systems, Inc. | Portable alarm system |
JPH08146130A (en) | 1994-11-24 | 1996-06-07 | Mitsubishi Electric Corp | Airport surface-ground running control system |
US5666157A (en) * | 1995-01-03 | 1997-09-09 | Arc Incorporated | Abnormality detection and surveillance system |
US5642285A (en) * | 1995-01-31 | 1997-06-24 | Trimble Navigation Limited | Outdoor movie camera GPS-position and time code data-logging for special effects production |
US5553609A (en) * | 1995-02-09 | 1996-09-10 | Visiting Nurse Service, Inc. | Intelligent remote visual monitoring system for home health care service |
US5751346A (en) * | 1995-02-10 | 1998-05-12 | Dozier Financial Corporation | Image retention and information security system |
US5689442A (en) | 1995-03-22 | 1997-11-18 | Witness Systems, Inc. | Event surveillance system |
US5629691A (en) * | 1995-05-26 | 1997-05-13 | Hughes Electronics | Airport surface monitoring and runway incursion warning system |
US5557278A (en) * | 1995-06-23 | 1996-09-17 | Northrop Grumman Corporation | Airport integrated hazard response apparatus |
US5627753A (en) * | 1995-06-26 | 1997-05-06 | Patriot Sensors And Controls Corporation | Method and apparatus for recording data on cockpit voice recorder |
US5926210A (en) * | 1995-07-28 | 1999-07-20 | Kalatel, Inc. | Mobile, ground-based platform security system which transmits images that were taken prior to the generation of an input signal |
US5835059A (en) | 1995-09-01 | 1998-11-10 | Lockheed Martin Corporation | Data link and method |
US5793416A (en) * | 1995-12-29 | 1998-08-11 | Lsi Logic Corporation | Wireless system for the communication of audio, video and data signals over a narrow bandwidth |
EP0883873B1 (en) * | 1996-02-29 | 1999-12-22 | Siemens Aktiengesellschaft | Airport guidance system, in particular airport surface movement guidance and control system |
US6587046B2 (en) * | 1996-03-27 | 2003-07-01 | Raymond Anthony Joao | Monitoring apparatus and method |
US5974158A (en) | 1996-03-29 | 1999-10-26 | The Commonwealth Of Australia Commonwealth Scientific And Industrial Research Organization | Aircraft detection system |
US5982418A (en) * | 1996-04-22 | 1999-11-09 | Sensormatic Electronics Corporation | Distributed video data storage in video surveillance system |
US5938706A (en) * | 1996-07-08 | 1999-08-17 | Feldman; Yasha I. | Multi element security system |
EP0821522B1 (en) * | 1996-07-23 | 2008-04-09 | Canon Kabushiki Kaisha | Camera control apparatus and method |
JP3862321B2 (en) * | 1996-07-23 | 2006-12-27 | キヤノン株式会社 | Server and control method thereof |
US6259475B1 (en) * | 1996-10-07 | 2001-07-10 | H. V. Technology, Inc. | Video and audio transmission apparatus for vehicle surveillance system |
US5798458A (en) | 1996-10-11 | 1998-08-25 | Raytheon Ti Systems, Inc. | Acoustic catastrophic event detection and data capture and retrieval system for aircraft |
JP3548352B2 (en) | 1996-10-25 | 2004-07-28 | キヤノン株式会社 | Remote camera control system, apparatus and method |
US6157317A (en) | 1996-12-02 | 2000-12-05 | Kline And Walker Llc | Secure communication and control system for monitoring, recording, reporting and/or restricting unauthorized use of vehicle. |
US5742336A (en) * | 1996-12-16 | 1998-04-21 | Lee; Frederick A. | Aircraft surveillance and recording system |
US5933098A (en) * | 1997-03-21 | 1999-08-03 | Haxton; Phil | Aircraft security system and method |
US6084510A (en) * | 1997-04-18 | 2000-07-04 | Lemelson; Jerome H. | Danger warning and emergency response system and method |
FR2763727B1 (en) * | 1997-05-20 | 1999-08-13 | Sagem | METHOD AND SYSTEM FOR GUIDING AN AIRPLANE TOWARDS A BERTH |
US6092008A (en) * | 1997-06-13 | 2000-07-18 | Bateman; Wesley H. | Flight event record system |
JP3085252B2 (en) * | 1997-07-31 | 2000-09-04 | 日本電気株式会社 | Remote control camera video relay system |
US6069655A (en) * | 1997-08-01 | 2000-05-30 | Wells Fargo Alarm Services, Inc. | Advanced video security system |
US6275231B1 (en) * | 1997-08-01 | 2001-08-14 | American Calcar Inc. | Centralized control and management system for automobiles |
US6570610B1 (en) * | 1997-09-15 | 2003-05-27 | Alan Kipust | Security system with proximity sensing for an electronic device |
US6002427A (en) | 1997-09-15 | 1999-12-14 | Kipust; Alan J. | Security system with proximity sensing for an electronic device |
US6930709B1 (en) * | 1997-12-04 | 2005-08-16 | Pentax Of America, Inc. | Integrated internet/intranet camera |
US6462697B1 (en) | 1998-01-09 | 2002-10-08 | Orincon Technologies, Inc. | System and method for classifying and tracking aircraft vehicles on the grounds of an airport |
US6584082B1 (en) * | 1998-01-16 | 2003-06-24 | Worldcom, Inc. | Apparatus, method and article of manufacture for transmitting data over a satellite |
US6078850A (en) * | 1998-03-03 | 2000-06-20 | International Business Machines Corporation | Method and apparatus for fuel management and for preventing fuel spillage |
US6385772B1 (en) * | 1998-04-30 | 2002-05-07 | Texas Instruments Incorporated | Monitoring system having wireless remote viewing and control |
US6278965B1 (en) * | 1998-06-04 | 2001-08-21 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Real-time surface traffic adviser |
US6002965A (en) * | 1998-06-10 | 1999-12-14 | Katz; Amiram | Self applied device and method for prevention of deep vein thrombosis |
US6522352B1 (en) * | 1998-06-22 | 2003-02-18 | Motorola, Inc. | Self-contained wireless camera device, wireless camera system and method |
US5999116A (en) | 1998-07-14 | 1999-12-07 | Rannoch Corporation | Method and apparatus for improving the surveillance coverage and target identification in a radar based surveillance system |
US6292098B1 (en) | 1998-08-31 | 2001-09-18 | Hitachi, Ltd. | Surveillance system and network system |
US6628835B1 (en) | 1998-08-31 | 2003-09-30 | Texas Instruments Incorporated | Method and system for defining and recognizing complex events in a video sequence |
IT1302866B1 (en) * | 1998-11-13 | 2000-10-10 | Telecom Italia Spa | ENVIRONMENTAL MONITORING APPARATUS ON TELEPHONE NETWORK. |
US6154658A (en) | 1998-12-14 | 2000-11-28 | Lockheed Martin Corporation | Vehicle information and safety control system |
US6720990B1 (en) * | 1998-12-28 | 2004-04-13 | Walker Digital, Llc | Internet surveillance system and method |
US6246320B1 (en) * | 1999-02-25 | 2001-06-12 | David A. Monroe | Ground link with on-board security surveillance system for aircraft and other commercial vehicles |
US7657330B2 (en) * | 1999-06-11 | 2010-02-02 | Parker-Hannifin Corporation | Optical ring architecture |
US6476858B1 (en) | 1999-08-12 | 2002-11-05 | Innovation Institute | Video monitoring and security system |
JP2001086486A (en) * | 1999-09-14 | 2001-03-30 | Matsushita Electric Ind Co Ltd | Monitor camera system and display method for monitor camera |
US6424370B1 (en) * | 1999-10-08 | 2002-07-23 | Texas Instruments Incorporated | Motion based event detection system and method |
US6358625B1 (en) * | 1999-10-11 | 2002-03-19 | H. C. Starck, Inc. | Refractory metals with improved adhesion strength |
US6698021B1 (en) * | 1999-10-12 | 2004-02-24 | Vigilos, Inc. | System and method for remote control of surveillance devices |
WO2001041000A1 (en) * | 1999-11-30 | 2001-06-07 | New Media Technology, Corp. | System and method for computer-assisted manual and automatic logging of time-based media |
US6646676B1 (en) | 2000-05-17 | 2003-11-11 | Mitsubishi Electric Research Laboratories, Inc. | Networked surveillance and control system |
WO2001093167A1 (en) * | 2000-05-31 | 2001-12-06 | Indivos Corporation | Biometric financial transaction system and method |
US6504479B1 (en) * | 2000-09-07 | 2003-01-07 | Comtrak Technologies Llc | Integrated security system |
US6932799B2 (en) * | 2000-10-19 | 2005-08-23 | Sca Hygiene Products Ab | Absorbent product with double barriers and single elastic system |
DE10053683A1 (en) * | 2000-10-28 | 2002-05-08 | Alcatel Sa | Image monitoring |
US7177448B1 (en) * | 2001-04-12 | 2007-02-13 | Ipix Corporation | System and method for selecting and transmitting images of interest to a user |
US7225338B2 (en) * | 2001-06-21 | 2007-05-29 | Sal Khan | Secure system for the identification of persons using remote searching of facial, iris and voice biometric templates |
US7136513B2 (en) * | 2001-11-08 | 2006-11-14 | Pelco | Security identification system |
US7221809B2 (en) * | 2001-12-17 | 2007-05-22 | Genex Technologies, Inc. | Face recognition system and method |
-
2003
- 2003-11-21 US US10/719,792 patent/US7634662B2/en not_active Expired - Fee Related
-
2009
- 2009-10-27 US US12/606,533 patent/US20100111377A1/en not_active Abandoned
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6940545B1 (en) * | 2000-02-28 | 2005-09-06 | Eastman Kodak Company | Face detecting camera and method |
US7200755B2 (en) * | 2001-05-24 | 2007-04-03 | Larry Hamid | Method and system for providing gated access for a third party to a secure entity or service |
US20030210139A1 (en) * | 2001-12-03 | 2003-11-13 | Stephen Brooks | Method and system for improved security |
US6853739B2 (en) * | 2002-05-15 | 2005-02-08 | Bio Com, Llc | Identity verification system |
Cited By (119)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8117252B2 (en) * | 2002-12-26 | 2012-02-14 | Schaff Glen D | Video-monitor/recording/playback system |
US20120236154A1 (en) * | 2002-12-26 | 2012-09-20 | Schaff Glen D | Video-monitor/recording/playback system |
US20040136388A1 (en) * | 2002-12-26 | 2004-07-15 | Schaff Glen D. | Video-monitor/recording/playback system |
US20090189984A1 (en) * | 2006-08-07 | 2009-07-30 | Ryuji Yamazaki | Object verification device and object verification method |
US8208028B2 (en) * | 2006-08-07 | 2012-06-26 | Panasonic Corporation | Object verification device and object verification method |
US20080226119A1 (en) * | 2007-03-16 | 2008-09-18 | Brant Candelore | Content image search |
US8861898B2 (en) * | 2007-03-16 | 2014-10-14 | Sony Corporation | Content image search |
US20080232651A1 (en) * | 2007-03-22 | 2008-09-25 | Artnix Inc. | Apparatus and method for detecting face region |
US9230151B2 (en) * | 2007-05-15 | 2016-01-05 | Samsung Electronics Co., Ltd. | Method, apparatus, and system for searching for image and image-related information using a fingerprint of a captured image |
US10296874B1 (en) | 2007-12-17 | 2019-05-21 | American Express Travel Related Services Company, Inc. | System and method for preventing unauthorized access to financial accounts |
US20090213221A1 (en) * | 2008-02-25 | 2009-08-27 | Canon Kabushiki Kaisha | Monitoring system, method for monitoring object entering room, and computer readable storage medium |
US9041811B2 (en) * | 2008-02-25 | 2015-05-26 | Canon Kabushiki Kaisha | Monitoring system, method for monitoring object entering room, and computer readable storage medium |
US20090251537A1 (en) * | 2008-04-02 | 2009-10-08 | David Keidar | Object content navigation |
US9398266B2 (en) * | 2008-04-02 | 2016-07-19 | Hernan Carzalo | Object content navigation |
US20110013003A1 (en) * | 2009-05-18 | 2011-01-20 | Mark Thompson | Mug shot acquisition system |
US10769412B2 (en) * | 2009-05-18 | 2020-09-08 | Mark Thompson | Mug shot acquisition system |
US20100295944A1 (en) * | 2009-05-21 | 2010-11-25 | Sony Corporation | Monitoring system, image capturing apparatus, analysis apparatus, and monitoring method |
US8982208B2 (en) * | 2009-05-21 | 2015-03-17 | Sony Corporation | Monitoring system, image capturing apparatus, analysis apparatus, and monitoring method |
US20110169631A1 (en) * | 2010-01-11 | 2011-07-14 | Ming-Hwa Sheu | Real-time alarm system |
US9367617B2 (en) * | 2010-05-13 | 2016-06-14 | Honeywell International Inc. | Surveillance system with direct database server storage |
US20140333777A1 (en) * | 2010-05-13 | 2014-11-13 | Honeywell International Inc. | Surveillance system with direct database server storage |
US20110317008A1 (en) * | 2010-06-29 | 2011-12-29 | Analogic Corporation | Airport/aircraft security |
US8155394B2 (en) * | 2010-07-13 | 2012-04-10 | Polaris Wireless, Inc. | Wireless location and facial/speaker recognition system |
US20120014567A1 (en) * | 2010-07-13 | 2012-01-19 | Polaris Wireless, Inc. | Wireless Location and Facial/Speaker Recognition System |
US20120019656A1 (en) * | 2010-07-23 | 2012-01-26 | Hon Hai Precision Industry Co., Ltd. | System and method for monitoring subjects of interest |
US20160103852A1 (en) * | 2010-09-24 | 2016-04-14 | Facebook, Inc. | Auto Tagging in Geo-Social Networking System |
US10176199B2 (en) * | 2010-09-24 | 2019-01-08 | Facebook, Inc. | Auto tagging in geo-social networking system |
US20120076367A1 (en) * | 2010-09-24 | 2012-03-29 | Erick Tseng | Auto tagging in geo-social networking system |
US8824748B2 (en) * | 2010-09-24 | 2014-09-02 | Facebook, Inc. | Auto tagging in geo-social networking system |
US9292518B2 (en) * | 2010-09-24 | 2016-03-22 | Facebook, Inc. | Auto-tagging in geo-social networking system |
US20140337341A1 (en) * | 2010-09-24 | 2014-11-13 | Facebook, Inc. | Auto-Tagging In Geo-Social Networking System |
US10402800B2 (en) * | 2010-10-14 | 2019-09-03 | Jpmorgan Chase Bank, N.A. | Image authentication and security system and method |
US20130246264A1 (en) * | 2010-10-14 | 2013-09-19 | Jpmorgan Chase Bank, N.A. | Image authentication and security system and method |
US11100481B2 (en) | 2010-10-14 | 2021-08-24 | Jpmorgan Chase Bank, N.A. | Image authentication and security system and method |
US8494961B1 (en) * | 2010-10-14 | 2013-07-23 | Jpmorgan Chase Bank, N.A. | Image authentication and security system and method |
US20120126939A1 (en) * | 2010-11-18 | 2012-05-24 | Hyundai Motor Company | System and method for managing entrance and exit using driver face identification within vehicle |
US8988188B2 (en) * | 2010-11-18 | 2015-03-24 | Hyundai Motor Company | System and method for managing entrance and exit using driver face identification within vehicle |
US8908034B2 (en) * | 2011-01-23 | 2014-12-09 | James Bordonaro | Surveillance systems and methods to monitor, recognize, track objects and unusual activities in real time within user defined boundaries in an area |
US20120188370A1 (en) * | 2011-01-23 | 2012-07-26 | James Bordonaro | Surveillance systems and methods to monitor, recognize, track objects and unusual activities in real time within user defined boundaries in an area |
US9317530B2 (en) | 2011-03-29 | 2016-04-19 | Facebook, Inc. | Face recognition based on spatial and temporal proximity |
US9984362B2 (en) | 2011-06-24 | 2018-05-29 | Liberty Peak Ventures, Llc | Systems and methods for gesture-based interaction with computer systems |
US8544729B2 (en) | 2011-06-24 | 2013-10-01 | American Express Travel Related Services Company, Inc. | Systems and methods for gesture-based interaction with computer systems |
US8701983B2 (en) | 2011-06-24 | 2014-04-22 | American Express Travel Related Services Company, Inc. | Systems and methods for gesture-based interaction with computer systems |
US20120330834A1 (en) * | 2011-06-24 | 2012-12-27 | American Express Travel Related Services Company, Inc. | Systems and methods for gesture-based interaction with computer systems |
US9483761B2 (en) | 2011-08-22 | 2016-11-01 | Iii Holdings 1, Llc | Methods and systems for contactless payments at a merchant |
US8714439B2 (en) | 2011-08-22 | 2014-05-06 | American Express Travel Related Services Company, Inc. | Methods and systems for contactless payments at a merchant |
US20130332509A1 (en) * | 2012-06-07 | 2013-12-12 | Universal City Studios Llc | Queue management system and method |
US10304276B2 (en) * | 2012-06-07 | 2019-05-28 | Universal City Studios Llc | Queue management system and method |
US11004290B2 (en) | 2012-06-07 | 2021-05-11 | Universal City Studios Llc | Queue management system and method |
RU2662919C2 (en) * | 2012-06-07 | 2018-07-31 | ЮНИВЕРСАЛ СИТИ СТЬЮДИОС ЭлЭлСи | Queue management system and method |
US20210329175A1 (en) * | 2012-07-31 | 2021-10-21 | Nec Corporation | Image processing system, image processing method, and program |
US9449407B2 (en) * | 2013-01-08 | 2016-09-20 | Google Inc. | Displaying dynamic content on a map based on user's location and scheduled task |
US20140192056A1 (en) * | 2013-01-08 | 2014-07-10 | Google Inc. | Displaying dynamic content on a map based on user's location and scheduled task |
US9967524B2 (en) * | 2013-01-10 | 2018-05-08 | Tyco Safety Products Canada Ltd. | Security system and method with scrolling feeds watchlist |
US10958878B2 (en) | 2013-01-10 | 2021-03-23 | Tyco Safety Products Canada Ltd. | Security system and method with help and login for customization |
US9615065B2 (en) | 2013-01-10 | 2017-04-04 | Tyco Safety Products Canada Ltd. | Security system and method with help and login for customization |
US10419725B2 (en) | 2013-01-10 | 2019-09-17 | Tyco Safety Products Canada Ltd. | Security system and method with modular display of information |
US20140195965A1 (en) * | 2013-01-10 | 2014-07-10 | Tyco Safety Products Canada Ltd. | Security system and method with scrolling feeds watchlist |
US11039108B2 (en) | 2013-03-15 | 2021-06-15 | James Carey | Video identification and analytical recognition system |
US11743431B2 (en) | 2013-03-15 | 2023-08-29 | James Carey | Video identification and analytical recognition system |
US9588988B2 (en) | 2013-03-15 | 2017-03-07 | Google Inc. | Visual indicators for temporal context on maps |
US11869325B2 (en) | 2013-03-15 | 2024-01-09 | James Carey | Video identification and analytical recognition system |
EP3668089A1 (en) * | 2013-04-19 | 2020-06-17 | James Carey | Video identification and analytical recognition system |
RU2760211C2 (en) * | 2013-04-19 | 2021-11-22 | Джеймс КАРЕЙ | Analytical recognition system |
US11100334B2 (en) | 2013-04-19 | 2021-08-24 | James Carey | Video identification and analytical recognition system |
US11587326B2 (en) | 2013-04-19 | 2023-02-21 | James Carey | Video identification and analytical recognition system |
WO2015006369A1 (en) * | 2013-07-08 | 2015-01-15 | Truestream Kk | Real-time analytics, collaboration, from multiple video sources |
WO2015025249A3 (en) * | 2013-08-23 | 2015-05-14 | Dor Givon | System for video based subject characterization, categorization, identification, tracking, monitoring and/or presence response |
US10123360B2 (en) * | 2014-01-22 | 2018-11-06 | Reliance Jio Infocomm Limited | System and method for secure wireless communication |
US11615663B1 (en) * | 2014-06-17 | 2023-03-28 | Amazon Technologies, Inc. | User authentication system |
US9477877B2 (en) | 2014-07-31 | 2016-10-25 | Landis+Gyr Innovations, Inc. | Asset security management system |
WO2016018613A1 (en) * | 2014-07-31 | 2016-02-04 | Landis+Gyr Innovations, Inc. | Asset security management system |
WO2016028142A1 (en) * | 2014-08-19 | 2016-02-25 | Ariff Faisal | A system for facilitating the identification and authorisation of travellers |
US11847589B2 (en) | 2014-08-20 | 2023-12-19 | Universal City Studios Llc | Virtual queuing system and method |
CN104464003A (en) * | 2014-12-04 | 2015-03-25 | 重庆晋才富熙科技有限公司 | Concentration checking method |
CN104464004A (en) * | 2014-12-04 | 2015-03-25 | 重庆晋才富熙科技有限公司 | Electronic signing device |
US10165307B2 (en) | 2015-06-16 | 2018-12-25 | Microsoft Technology Licensing, Llc | Automatic recognition of entities in media-captured events |
US9704020B2 (en) | 2015-06-16 | 2017-07-11 | Microsoft Technology Licensing, Llc | Automatic recognition of entities in media-captured events |
US10276007B2 (en) * | 2015-08-27 | 2019-04-30 | Panasonic Intellectual Property Management Co., Ltd. | Security system and method for displaying images of people |
US10991219B2 (en) | 2015-08-27 | 2021-04-27 | Panasonic I-Pro Sensing Solutions Co., Ltd. | Security system and method for displaying images of people |
US11670126B2 (en) | 2016-03-16 | 2023-06-06 | Universal City Studios Llc | Virtual queue system and method |
US11182998B2 (en) | 2016-03-16 | 2021-11-23 | Universal City Studios Llc | Virtual queue system and method |
US10580244B2 (en) | 2016-03-16 | 2020-03-03 | Universal City Studios Llc | Virtual queue system and method |
US10152840B2 (en) | 2016-03-16 | 2018-12-11 | Universal City Studios Llc | Virtual queue system and method |
CN106169071A (en) * | 2016-07-05 | 2016-11-30 | 厦门理工学院 | A kind of Work attendance method based on dynamic human face and chest card recognition and system |
US9866916B1 (en) * | 2016-08-17 | 2018-01-09 | International Business Machines Corporation | Audio content delivery from multi-display device ecosystem |
WO2018075443A1 (en) * | 2016-10-17 | 2018-04-26 | Muppirala Ravikumar | Remote identification of person using combined voice print and facial image recognition |
US10679490B2 (en) | 2016-10-17 | 2020-06-09 | Md Enterprises Global Llc | Remote identification of person using combined voice print and facial image recognition |
US11775883B2 (en) | 2016-11-09 | 2023-10-03 | Universal City Studios Llc | Virtual queuing techniques |
US10943188B2 (en) | 2016-11-09 | 2021-03-09 | Universal City Studios Llc | Virtual queuing techniques |
WO2018213594A3 (en) * | 2017-05-19 | 2019-05-09 | Walmart Apollo, Llc | System and method for smart facilities monitoring |
US10581975B2 (en) | 2017-05-19 | 2020-03-03 | Walmart Apollo, Llc | System and method for smart facilities monitoring |
US10902482B2 (en) * | 2017-07-19 | 2021-01-26 | Toshiba Tec Kabushiki Kaisha | Server apparatus |
US20190026794A1 (en) * | 2017-07-19 | 2019-01-24 | Toshiba Tec Kabushiki Kaisha | Server apparatus |
RU2692269C2 (en) * | 2017-10-13 | 2019-06-24 | Федеральное Государственное унитарное предприятие Государственный научно-исследовательский институт гражданской авиации (ФГУП ГосНИИ ГА) | Method of determining level of transport safety of rf civil aviation facilities |
US11776308B2 (en) | 2017-10-25 | 2023-10-03 | Johnson Controls Tyco IP Holdings LLP | Frictionless access control system embodying satellite cameras for facial recognition |
WO2019084133A1 (en) * | 2017-10-25 | 2019-05-02 | Sensormatic Electronics, LLC | Frictionless access control system embodying satellite cameras for facial recognition |
US10657782B2 (en) | 2017-12-21 | 2020-05-19 | At&T Intellectual Property I, L.P. | Networked premises security |
CN108346191A (en) * | 2018-02-06 | 2018-07-31 | 中国平安人寿保险股份有限公司 | Work attendance method, device, computer equipment and storage medium |
CN108492393A (en) * | 2018-03-16 | 2018-09-04 | 百度在线网络技术(北京)有限公司 | Method and apparatus for registering |
CN108629862A (en) * | 2018-04-16 | 2018-10-09 | 上海呈合信息科技有限公司 | It registers method and device |
US11189164B2 (en) | 2018-04-27 | 2021-11-30 | Cubic Corporation | Modifying operational settings of a traffic signal |
US11688202B2 (en) | 2018-04-27 | 2023-06-27 | Honeywell International Inc. | Facial enrollment and recognition system |
CN109271547A (en) * | 2018-07-19 | 2019-01-25 | 国政通科技有限公司 | A kind of tourist's technique for delineating, device and system based on scenic spot real name |
US11176629B2 (en) * | 2018-12-21 | 2021-11-16 | FreightVerify, Inc. | System and method for monitoring logistical locations and transit entities using a canonical model |
US11348367B2 (en) * | 2018-12-28 | 2022-05-31 | Homeland Patrol Division Security, Llc | System and method of biometric identification and storing and retrieving suspect information |
AU2020202221A1 (en) * | 2019-03-29 | 2020-10-22 | Round Pixel Pty Ltd | Privacy preserving visitor recognition and movement pattern analysis based on computer vision |
CN110276851A (en) * | 2019-04-28 | 2019-09-24 | 国家电投集团黄河上游水电开发有限责任公司 | A kind of method and its inspection device carrying out intelligent patrol detection in photovoltaic plant using unmanned plane |
US20220198827A1 (en) * | 2019-06-25 | 2022-06-23 | Motorola Solutions, Inc. | System and method for saving bandwidth in performing facial recognition |
US11935325B2 (en) * | 2019-06-25 | 2024-03-19 | Motorola Solutions, Inc. | System and method for saving bandwidth in performing facial recognition |
US11568333B2 (en) | 2019-06-27 | 2023-01-31 | Universal City Studios Llc | Systems and methods for a smart virtual queue |
US11443036B2 (en) * | 2019-07-30 | 2022-09-13 | Hewlett Packard Enterprise Development Lp | Facial recognition based security by a management controller |
US11283937B1 (en) * | 2019-08-15 | 2022-03-22 | Ikorongo Technology, LLC | Sharing images based on face matching in a network |
US11902477B1 (en) * | 2019-08-15 | 2024-02-13 | Ikorongo Technology, LLC | Sharing images based on face matching in a network |
EP4029000A4 (en) * | 2019-09-13 | 2023-12-20 | Royal Caribbean Cruises Ltd. | Facial recognition system and methods for identity credentialing and personalized services |
WO2021050237A1 (en) * | 2019-09-13 | 2021-03-18 | Royal Caribbean Cruises Ltd. | Facial recognition system and methods for identity credentialing and personalized services |
US20210397823A1 (en) * | 2019-09-17 | 2021-12-23 | Verizon Media Inc. | Computerized system and method for adaptive stranger detection |
CN111951424A (en) * | 2020-06-29 | 2020-11-17 | 山东汇佳软件科技股份有限公司 | Intelligent management system for dormitory |
CN112887343A (en) * | 2021-05-06 | 2021-06-01 | 广东电网有限责任公司佛山供电局 | Management system and management method for network big data |
Also Published As
Publication number | Publication date |
---|---|
US7634662B2 (en) | 2009-12-15 |
US20040117638A1 (en) | 2004-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7634662B2 (en) | Method for incorporating facial recognition technology in a multimedia surveillance system | |
US11290693B2 (en) | System for automatically triggering a recording | |
US7683929B2 (en) | System and method for video content analysis-based detection, surveillance and alarm management | |
US9875392B2 (en) | System and method for face capture and matching | |
US6975346B2 (en) | Method for suspect identification using scanning of surveillance media | |
US7769207B2 (en) | System and method for collection, storage, and analysis of biometric data | |
US20040240542A1 (en) | Method and apparatus for video frame sequence-based object tracking | |
CN109214274B (en) | Airport security management system | |
US8089340B2 (en) | Real-time screening interface for a vehicle screening system | |
Norris | From personal to digital: CCTV, the panopticon, and the technological mediation of suspicion and social control | |
US20070036395A1 (en) | Reverse identity profiling system with alert function | |
US20050128304A1 (en) | System and method for traveler interactions management | |
US7109869B2 (en) | Method and system for facility security | |
US20110257985A1 (en) | Method and System for Facial Recognition Applications including Avatar Support | |
US20070122003A1 (en) | System and method for identifying a threat associated person among a crowd | |
US20210196169A1 (en) | Methods and System for Monitoring and Assessing Employee Moods | |
US20040263621A1 (en) | Customer service counter/checkpoint registration system with video/image capturing, indexing, retrieving and black list matching function | |
JP2003187352A (en) | System for detecting specified person | |
Li et al. | Face recognition applications | |
US20100033572A1 (en) | Ticket-holder security checkpoint system for deterring terrorist attacks | |
US20220262185A1 (en) | Identity Determination Using Biometric Data | |
WO2003075119A2 (en) | A system and method for traveler interactions management | |
Lazarick | Applications of technology in airport access control | |
Zhang | Smart solutions to airport security in post-COVID-19 era | |
KR102420151B1 (en) | Mobile ondemand cctv system based on collective cross check and tracking |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |