US20120293661A1 - Optimizing video stream processing - Google Patents
Optimizing video stream processing Download PDFInfo
- Publication number
- US20120293661A1 US20120293661A1 US13/559,996 US201213559996A US2012293661A1 US 20120293661 A1 US20120293661 A1 US 20120293661A1 US 201213559996 A US201213559996 A US 201213559996A US 2012293661 A1 US2012293661 A1 US 2012293661A1
- Authority
- US
- United States
- Prior art keywords
- transaction
- units
- individual
- processor
- priority
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/20—Point-of-sale [POS] network systems
- G06Q20/202—Interconnection or interaction of plural electronic cash registers [ECR] or to host computer, e.g. network details, transfer of information from host to ECR or from ECR to ECR
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/96—Management of image or video recognition tasks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position
Definitions
- the present invention generally relates to video surveillance, and more particularly relates to using a computer infrastructure to prioritize the processing of multiple video streams.
- Video surveillance in a retail environment is a common practice. However, it remains resource intensive to process captured video to automatically detect irregular activities.
- irregular activities such as cashier frauds at check-out lanes
- sophisticated and resource intensive computerized pattern recognition algorithms need to be executed. By multiplying by the scale of the lanes ( 10 - 20 each store and thousands nationwide), a significant amount of computational power is required to handle the huge volume of output generated by complex computer processing.
- each store usually has only limited space and resources to handle all point-of-sale (POS) transactions and associated video streams.
- Available space may be sufficient for smaller stores that have fewer lanes, but it is not sufficient for larger stores with 15 ⁇ 20 lanes, or even more.
- retailers are not always willing to invest more into the hardware, software and services necessary to keep up with the need.
- a method is implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable storage medium having programming instructions. The method determines processing priority for each transaction unit of individual transaction units comprising video and transaction data; and processing the individual transaction units based on the priority for each transaction unit.
- a computer program product comprising a computer readable storage medium having computer readable program code embodied in the storage medium, the computer program product includes at least one module operable to determine processing priority for each transaction unit of individual transaction units comprising video and transaction data; and process the individual transaction units based on the priority for each transaction unit.
- a system for processing video comprising a memory; and at least one processor coupled to said memory and operative to determine processing priority for each transaction unit of individual transaction units comprising video and transaction data; and process the individual transaction units based on the priority for each transaction unit.
- FIG. 1 shows an illustrative environment for a system for prioritizing multiple video streams processing according to an embodiment of the invention.
- FIG. 2 shows a close up of an illustrative environment for prioritizing multiple video streams processing according to an embodiment of the invention.
- FIG. 3 illustrates a system diagram of an exemplary intelligent switching program according to an embodiment of the invention.
- FIGS. 4A and 4B illustrate examples of calculating priorities for different transaction units.
- FIG. 5 illustrates a flowchart for exemplary steps of prioritizing multiple video streams processing according to an embodiment of the invention.
- FIG. 6 illustrates a flowchart for exemplary steps of assigning priorities for multiple video streams.
- the present invention generally relates to video surveillance, and more particularly relates to using a computer infrastructure to prioritize the processing of multiple video streams in a retail environment.
- aspects of the invention aim to address the scalability issue encountered in retail stores, where computational power is often insufficient to monitor all check-out lanes simultaneously for irregular activities such as cashier frauds, particularly during periods of high activity (e.g., during the holiday shopping season).
- aspects of the invention involve implementation of an intelligent switching program, whereby the processing power required to monitor check-out stations is considerably reduced.
- the present invention monitors a subset of check-out stations at any given time, instead of monitoring all check-out stations at all times.
- the subset of check-out stations may be determined dynamically according to, but not limited to, cashier records, input parameters from the manager, current lane activity, past lane activity, time of day, etc.
- Statistical models e.g., effective population sampling and/or population hypothesis tests, are developed based on the above variables to guide the lane selection process, whereby increases in the false-negative rate due to failure to monitor particular lanes when events of interest occur are controlled.
- the present invention develops an intelligent switching program for lane selection and dynamically allocates processing power to different lanes from time to time.
- the system is also capable of dynamically adjusting its allocation based on real-time incoming data.
- the processing power can be located at a different location from the check-out lanes and can monitor check-out lanes from more than one store at various locations.
- the processing power can also process historical data along with real-time data.
- a regional or national processing center may provide backup to any overloaded individual store.
- each store initially has its own scheduling and prioritization procedures to handle its own transactions. If there are transactions with high priorities that cannot be handled by local computational resources, a request will be sent to the regional or national processing center to process the load. Since different stores may have different problem definitions, the higher level processing unit does not necessarily contain the same analytic modules as individual stores do.
- the processing unit at the regional or national processing center may just provide the computational power, while what to compute is defined by the requests sent by the individual stores.
- the requests sent by the individual stores include the transaction data, video streams and the task definitions.
- Transaction data refers to data from POS devices including customer number, prices, item numbers, quantities, discounts, voids, etc.
- the processing units could reside in the same physical location, or they could be in distributed form and be referenced by their virtual/logical addresses.
- the processing power may rely on a set of initial rules that are capable of being dynamically updated.
- the initial input of the monitoring system may include, but is not limited to: user preference, e.g., Lane 10 is considered sensitive and so should have more focus than other lanes; more focus should be placed on a particular cashier when he or she is on duty; historical data: e.g., the transaction volume on past Sundays, usual time of day, date, day of the week, etc.
- a set of statistical sampling and population estimation techniques e.g., hypothesis testing are employed to further enforce the confidence of the prioritization process.
- the selective monitoring unit may initiate a statistical sampling process to allocate computational resources, such that the lanes or the lanes occupied by certain cashiers receive more focus than others.
- the sampling process is based on statistical inference techniques with context-aware (retail) prior information and mathematical models.
- the intelligent switching program may adjust its focus to lanes with a higher processing rate.
- the system should have a different profile for different time periods during a day. This could be pre-defined as the initial input.
- the volume of particular types of transactions can trigger the intelligent switching program to change focus. For instance, if one lane produces more “void transaction” events than others, the system may adjust its focus to process more transactions from this lane. In other words, if a lane/cashier produces more “candidate” irregular activities such as cashier frauds, the system may put more focus on the lane and/or cashier.
- the event triggers for the intelligent switching program to switch focus may not be evaluated independently from each other. Rather, they may be modeled as a joint distribution as there may be a strong correlation among them. Common feature models may be used, such as Gaussian, Poisson, exponential, uniform, etc.
- hypothesis tests and statistical sampling processes are carefully designed such that the target irregular activity capture accuracy is maintained, e.g., how many items from a lane and/or a cashier the system should process to maintain a 75% capture rate. This is highly context related, and standard statistical methods are modified to fit an application.
- a prescheduling module determines whether a particular lane should be monitored at any given time based on whether the lane is open. Prior to the processing by the intelligent switching program to prioritize the processing of the video streams, some preprocessing is performed by a preprocessing module on all lanes to produce intermediate transactions. These intermediate transactions provide transaction units for further processing.
- a transaction unit contains transaction video which corresponds to a set of items purchased by a single customer in a single span of time.
- the intermediate features along with prior information are used to decide which transactions should receive prioritized processing (e.g., to catch cashier irregular activity).
- Results are archived for human perusal and validation.
- FIG. 1 shows an illustrative environment for prioritizing the processing of multiple video streams according to an embodiment of the invention.
- at least one camera 42 captures activities in a checkout lane.
- Camera 44 and camera 46 each capture activities in a different checkout lane.
- a digital video input 41 from camera 42 a digital video input 43 from camera 44 , a digital video input N from camera 46 are obtained and sent to a system 12 that includes, for example, an intelligent switching program 30 , data 50 , parameters 52 , output 54 and/or the like, as discussed herein.
- Transaction data 47 , 48 , and M from the each of the checkout lanes are sent to system 12 to be processed.
- FIG. 2 shows a closer view of an illustrative environment 10 for prioritizing the processing of multiple video streams according to an embodiment of the invention.
- environment 10 includes a computer system 12 that can perform the process described herein in order to detect irregular checkout activities.
- computer system 12 is shown including a computing device 14 that comprises an intelligent switching program 30 , which makes computing device 14 operable for prioritizing the processing of multiple video streams, by performing the process described herein.
- Computing device 14 is shown including a processor 20 , a memory 22 A, an input/output (I/O) interface 24 , and a bus 26 . Further, computing device 14 is shown in communication with an external I/O device/resource 28 and a storage device 22 B.
- processor 20 executes program code, such as intelligent switching program 30 , which is stored in a storage system, such as memory 22 A and/or storage device 22 B. While executing program code, processor 20 can read and/or write data, such as data 36 to/from memory 22 A, storage device 22 B, and/or I/O interface 24 .
- Bus 26 provides a communications link between each of the components in computing device 14 .
- I/O device 28 can comprise any device that transfers information between a user 16 and computing device 14 and/or digital video input 41 , 43 , N and transaction data input 47 , 48 , M and computing device 14 .
- I/O device 28 can comprise a user I/O device to enable an individual user 16 to interact with computing device 14 and/or a communications device to enable an element, such as digital video input 41 , 43 , N and transaction data input 47 , 48 , M to communicate with computing device 14 using any type of communications link.
- computing device 14 can comprise any general purpose computing article of manufacture capable of executing program code installed thereon.
- computing device 14 and intelligent switching program 30 are only representative of various possible equivalent computing devices that may perform the process described herein.
- the functionality provided by computing device 14 and intelligent switching program 30 can be implemented by a computing article of manufacture that includes any combination of general and/or specific purpose hardware and/or program code.
- the program code and hardware can be created using standard programming and engineering techniques, respectively. Such standard programming and engineering techniques include an open architecture to allow integration of processing from different retailers. Such an open architecture includes cloud computing.
- computer system 12 is only illustrative of various types of computer systems for implementing aspects of the invention.
- computer system 12 comprises two or more computing devices that communicate over any type of communications link, such as a network, a shared memory, or the like, to perform the process described herein.
- any type of communications link such as a network, a shared memory, or the like
- one or more computing devices in computer system 12 can communicate with one or more other computing devices external to computer system 12 using any type of communications link.
- the communications link can comprise any combination of various types of wired and/or wireless links; comprise any combination of one or more types of networks; and/or utilize any combination of various types of transmission techniques and protocols.
- intelligent switching program 30 enables computer system 12 to detect irregular checkout activities.
- intelligent switching program 30 is shown including a prescheduling module 32 , a preprocessing module 34 , a prioritizing module 36 , a processing module 37 , a cleanup module 38 , and an archiving module 39 . Operation of each of these modules is discussed further herein. However, it is understood that some of the various modules shown in FIG. 2 can be implemented independently, combined, and/or stored in memory of one or more separate computing devices that are included in computer system 12 . Further, it is understood that some of the modules and/or functionality may not be implemented, or additional modules and/or functionality may be included as part of computer system 12 .
- FIG. 3 illustrates a system diagram of an exemplary video transaction intelligent switching program 30 ( FIG. 2 ).
- the present invention contemplates a plurality of lanes in one or more retail stores.
- This non-limiting example depicts a system prioritizing the processing of multiple video streams installed in a retail store.
- the retail store maintains an arbitrary number of lanes.
- Cameras are installed to capture transaction activities at each lane.
- Transaction data e.g., prices, item numbers, quantities, etc.
- the transaction includes both the transaction data and the video stream.
- This non-limiting example assumes that there are N lanes (lane 1 to lane N) to be processed as determined by a prescheduling module 32 ( FIG. 2 ).
- a prescheduling filter 111 is installed for lane 1 .
- another filter 112 is installed for lane 2
- filter 113 is installed for lane N- 1
- filter 114 for lane N.
- the prescheduling filters determine whether a transaction from a particular lane should be monitored based on whether the lane is open. All transactions from lanes are sent to the preprocessing module 34 ( FIG. 2 ). The preprocessing module 34 organizes the transactions such that each transaction is isolated and given a unique ID. All transactions are then presented to the prioritizing module 36 . The prioritizing module 36 uses predetermined rules, which are also capable of being dynamically updated, to calculate a priority score for each transaction.
- the prioritizing module 36 maintains a transaction priority queue 140 , which contains transactions with priority scores. Transactions are listed in the transaction priority queue 140 in the order of their priority score.
- the processing module 37 processes transactions with the highest priority score first from the transaction priority queue 140 .
- the processing module 37 contains the relatively computationally-intensive irregular activity detection software to analyze each transaction to discover whether irregular activity has occurred for that particular transaction. As a transaction is processed by the processing module 37 , the transaction unit for that transaction is moved to an archival queue 170 .
- a cleanup module 38 monitors the transaction priority queue 140 at regular time intervals. If a transaction has been in the transaction priority queue 140 for more than a predetermined amount of time (e.g., 10 seconds) and the priority score for the transaction is low, the cleanup module 38 will move the transaction to the archival queue 170 .
- a predetermined amount of time e.g. 10 seconds
- the archiving module 39 processes transaction units in the archival queue 170 by moving the transaction units in the archival queue 170 to persistent storage 190 . From persistent storage 190 , data can be extracted to form part of prioritizing rules 195 . Human operator 16 can also provide prioritizing rules 195 . Prioritizing rules 195 are used by the prioritizing module 36 to prioritize transactions.
- unprocessed transactions from the persistent storage 190 can be sent back to the prioritizing module 36 to be reprocessed
- FIGS. 4A and 4B illustrate two stages of priority setting among transactions.
- FIG. 4A illustrates a first stage of prioritizing transactions. In this first stage, transactions from Lanes 1 - 3 are sent to the prioritizing module 36 . Based on the prioritizing rules provided by human operator 16 and the characteristics of each transaction, the prioritizing module 36 prioritizes transactions in the order of T 1 to T N with T 1 having the highest priority.
- T 1 from Lane 1 has the highest priority because the cashier operating Lane 1 has been flagged by the manager.
- T 2 from Lane 2 is given a high priority because the transaction contains three voided items.
- T 3 from Lane 3 is also given a high priority because the entire transaction is voided.
- the priority given to T 2 is higher than that of T 3 because three voided items in a single transaction is considered a more irregular activity than voiding an entire transaction, according to the system rule design.
- T 4 from Lane 2 is given a high priority because the transaction contains unusually long durations between item scans.
- T 4 is given a lower priority than T 1 -T 3 .
- T N from Lane 2 is given low priority because it is a seemingly ordinary transaction.
- FIG. 4B illustrates a second stage of prioritizing transactions.
- the prioritizing rules have been updated with the transaction data from the first stage.
- the cashier from Lane 2 issued multiple suspicious transactions.
- the prioritizing rules were updated based on this information.
- T 1 from Lane 2 is given top priority because the first stage showed multiple suspicious transactions from the same cashier and a large number of high value items.
- T 2 from Lane 3 is given a high priority because the same cashier from Lane 3 had two managerial overwrites issued.
- T 3 from Lane 3 is given high priority because the same cashier is considered suspicious.
- T 4 is given high priority because a customer pays cash. Paying in cash means that the identity of buyer is not recorded as it would be, for example, in a credit card transaction, so there is a correlation between cash purchases and fraud. However, the correlation is not very strong relative to the items that are prioritized ahead of it.
- T N is given low priority because a different cashier now works at Lane 1 and the cashier is not flagged as suspicious.
- the transaction T N is an ordinary, non-suspicious transaction.
- FIG. 5 illustrates a flowchart for exemplary steps of assigning priorities for transaction units.
- the intelligent switching program takes initial input for assigning priorities.
- the intelligent switching program initiates a statistical sampling model to process transactional data and video stream, which is combined into a transaction unit.
- the intelligent switching program analyzes features of each transaction unit.
- the features includes but are not limited to: activity level at each lane, e.g., can be obtained by analyzing the object detection and tracking algorithms; volume of transactions in terms of both number of transactions and monetary amounts; and results of irregular activity detections in the near history which is also used to update the historical data to affect future transaction priority ordering.
- step 504 the intelligent system uses statistical models (e.g., Gaussian, Poisson, exponential, uniform, etc.) to determine correlations between features of the transaction units.
- step 505 each transaction unit is given a priority score based on analysis results and placed in the transaction priority queue.
- FIG. 6 illustrates a flowchart for exemplary steps of processing transactions according to the present invention.
- the monitoring system preprocesses video capture and transaction data and turns them into identifiable individual transaction units.
- the prioritizing system prioritizes the individual transaction units based on priority rules.
- the system determines whether a transaction unit has high enough priority to be processed. If the transaction unit has relatively high priority, the transaction is processed in step 604 . If the transaction unit does not have high priority in step 603 , the transaction unit is archived directly in step 605 . After the transaction unit is processed in step 604 , irregular activities are captured and reported in step 606 . Processed transactions from step 604 are also archived in step 605 . An analysis of all transactions from step 605 provides the basis for updating prioritizing rules in step 607 .
Abstract
An approach to reduce the processing power required to monitor check-out stations. A subset of check-out stations may be monitored at any given time, instead of monitoring all check-out stations at all times. The subset of check-out stations is determined dynamically according to, but not limited to, cashier records, input parameters from the user, current lane activity, past lane activity, time of day, etc. Statistical models (e.g., effective population sampling and/or population hypothesis tests) are developed along these lines that guide the lane selection process, whereby increases in the false-negative rate due to failure to monitor particular lanes when events of interest occur are controlled. By monitoring fewer check-out stations, while maintaining target performance accuracy, the amount of data that end users must deal with is significantly reduced.
Description
- This application is a continuation of U.S. application Ser. No. 12/697,530, filed Feb. 1, 2010.
- The present invention generally relates to video surveillance, and more particularly relates to using a computer infrastructure to prioritize the processing of multiple video streams.
- Video surveillance in a retail environment is a common practice. However, it remains resource intensive to process captured video to automatically detect irregular activities. In retail environment, in order to automatically capture irregular activities such as cashier frauds at check-out lanes, sophisticated and resource intensive computerized pattern recognition algorithms need to be executed. By multiplying by the scale of the lanes (10-20 each store and thousands nationwide), a significant amount of computational power is required to handle the huge volume of output generated by complex computer processing.
- In addition, each store usually has only limited space and resources to handle all point-of-sale (POS) transactions and associated video streams. Available space may be sufficient for smaller stores that have fewer lanes, but it is not sufficient for larger stores with 15˜20 lanes, or even more. At the same time, retailers are not always willing to invest more into the hardware, software and services necessary to keep up with the need.
- As a result, if the available computational resources cannot keep up with the need, useful information will be dropped due to this shortage, e.g., frames are dropped in the video streams and/or processing is limited to only a subset of video streams. This may cause many irregular activities to be missed, resulting in severe loss to the retailers.
- In view of the foregoing, a need exists to overcome one or more of the deficiencies in the related art.
- In one aspect of the present invention, a method is implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable storage medium having programming instructions. The method determines processing priority for each transaction unit of individual transaction units comprising video and transaction data; and processing the individual transaction units based on the priority for each transaction unit.
- In another aspect of the present invention, there provides a computer program product comprising a computer readable storage medium having computer readable program code embodied in the storage medium, the computer program product includes at least one module operable to determine processing priority for each transaction unit of individual transaction units comprising video and transaction data; and process the individual transaction units based on the priority for each transaction unit.
- In yet another aspect of the present invention, there provides a system for processing video, comprising a memory; and at least one processor coupled to said memory and operative to determine processing priority for each transaction unit of individual transaction units comprising video and transaction data; and process the individual transaction units based on the priority for each transaction unit.
- These and other features of the invention will be more readily understood from the following detailed description of the various aspects of the invention taken in conjunction with the accompanying drawings that depict various embodiments of the invention, in which:
-
FIG. 1 shows an illustrative environment for a system for prioritizing multiple video streams processing according to an embodiment of the invention. -
FIG. 2 shows a close up of an illustrative environment for prioritizing multiple video streams processing according to an embodiment of the invention. -
FIG. 3 illustrates a system diagram of an exemplary intelligent switching program according to an embodiment of the invention. -
FIGS. 4A and 4B illustrate examples of calculating priorities for different transaction units. -
FIG. 5 illustrates a flowchart for exemplary steps of prioritizing multiple video streams processing according to an embodiment of the invention. -
FIG. 6 illustrates a flowchart for exemplary steps of assigning priorities for multiple video streams. - It is noted that the drawings are not to scale. The drawings are intended to depict only typical aspects of the invention, and therefore should not be considered as limiting the scope of the invention. In the drawings, like numbering represents like elements between the drawings.
- The present invention generally relates to video surveillance, and more particularly relates to using a computer infrastructure to prioritize the processing of multiple video streams in a retail environment.
- Aspects of the invention aim to address the scalability issue encountered in retail stores, where computational power is often insufficient to monitor all check-out lanes simultaneously for irregular activities such as cashier frauds, particularly during periods of high activity (e.g., during the holiday shopping season).
- Aspects of the invention involve implementation of an intelligent switching program, whereby the processing power required to monitor check-out stations is considerably reduced. In an embodiment, the present invention monitors a subset of check-out stations at any given time, instead of monitoring all check-out stations at all times. The subset of check-out stations may be determined dynamically according to, but not limited to, cashier records, input parameters from the manager, current lane activity, past lane activity, time of day, etc. Statistical models, e.g., effective population sampling and/or population hypothesis tests, are developed based on the above variables to guide the lane selection process, whereby increases in the false-negative rate due to failure to monitor particular lanes when events of interest occur are controlled. By monitoring fewer check-out stations, while maintaining target performance accuracy, the amount of data that end users must deal with is significantly reduced.
- According to an embodiment of the invention, it is assumed that there are N check-out lanes to monitor and a single processing machine equipped with an irregular activity capture module. During any unit time period, e.g., 10 seconds, the system may be able to process a desired number of transactions. Thus, the present invention develops an intelligent switching program for lane selection and dynamically allocates processing power to different lanes from time to time. The system is also capable of dynamically adjusting its allocation based on real-time incoming data.
- In an embodiment of the invention, the processing power can be located at a different location from the check-out lanes and can monitor check-out lanes from more than one store at various locations. The processing power can also process historical data along with real-time data.
- According to an embodiment of the invention, there may be shared computational resources among different retail stores. For example, a regional or national processing center may provide backup to any overloaded individual store. In this case, each store initially has its own scheduling and prioritization procedures to handle its own transactions. If there are transactions with high priorities that cannot be handled by local computational resources, a request will be sent to the regional or national processing center to process the load. Since different stores may have different problem definitions, the higher level processing unit does not necessarily contain the same analytic modules as individual stores do.
- The processing unit at the regional or national processing center may just provide the computational power, while what to compute is defined by the requests sent by the individual stores. The requests sent by the individual stores include the transaction data, video streams and the task definitions. Transaction data refers to data from POS devices including customer number, prices, item numbers, quantities, discounts, voids, etc. The processing units could reside in the same physical location, or they could be in distributed form and be referenced by their virtual/logical addresses.
- Further embodiments of the present invention provide an open architecture to integrate processing from different locations as well as different retailers. When the computational resource of one vendor is limited, a higher-level processing unit could allocate free resources from another vendor to assume the burden.
- In prioritizing the processing of multiple video streams, the processing power may rely on a set of initial rules that are capable of being dynamically updated. The initial input of the monitoring system may include, but is not limited to: user preference, e.g., Lane 10 is considered sensitive and so should have more focus than other lanes; more focus should be placed on a particular cashier when he or she is on duty; historical data: e.g., the transaction volume on past Sundays, usual time of day, date, day of the week, etc. A set of statistical sampling and population estimation techniques (e.g., hypothesis testing) are employed to further enforce the confidence of the prioritization process.
- Based on the initial system input described above, the selective monitoring unit may initiate a statistical sampling process to allocate computational resources, such that the lanes or the lanes occupied by certain cashiers receive more focus than others. The sampling process is based on statistical inference techniques with context-aware (retail) prior information and mathematical models.
- In an embodiment of the invention, as the system continues to be provided with new information, it can dynamically adjust its computational resource allocation. To maintain the target capture accuracy, the intelligent switching program may adjust its focus to lanes with a higher processing rate. The system should have a different profile for different time periods during a day. This could be pre-defined as the initial input. In addition, the volume of particular types of transactions can trigger the intelligent switching program to change focus. For instance, if one lane produces more “void transaction” events than others, the system may adjust its focus to process more transactions from this lane. In other words, if a lane/cashier produces more “candidate” irregular activities such as cashier frauds, the system may put more focus on the lane and/or cashier.
- In an embodiment of the invention, the event triggers for the intelligent switching program to switch focus may not be evaluated independently from each other. Rather, they may be modeled as a joint distribution as there may be a strong correlation among them. Common feature models may be used, such as Gaussian, Poisson, exponential, uniform, etc.
- Hypothesis tests and statistical sampling processes are carefully designed such that the target irregular activity capture accuracy is maintained, e.g., how many items from a lane and/or a cashier the system should process to maintain a 75% capture rate. This is highly context related, and standard statistical methods are modified to fit an application.
- In addition, a prescheduling module determines whether a particular lane should be monitored at any given time based on whether the lane is open. Prior to the processing by the intelligent switching program to prioritize the processing of the video streams, some preprocessing is performed by a preprocessing module on all lanes to produce intermediate transactions. These intermediate transactions provide transaction units for further processing. A transaction unit contains transaction video which corresponds to a set of items purchased by a single customer in a single span of time.
- The intermediate features along with prior information are used to decide which transactions should receive prioritized processing (e.g., to catch cashier irregular activity). Results are archived for human perusal and validation.
- Turning to the drawings,
FIG. 1 shows an illustrative environment for prioritizing the processing of multiple video streams according to an embodiment of the invention. To this extent, at least onecamera 42 captures activities in a checkout lane.Camera 44 andcamera 46 each capture activities in a different checkout lane. Accordingly, adigital video input 41 fromcamera 42, adigital video input 43 fromcamera 44, a digital video input N fromcamera 46 are obtained and sent to asystem 12 that includes, for example, anintelligent switching program 30,data 50,parameters 52,output 54 and/or the like, as discussed herein.Transaction data system 12 to be processed. -
FIG. 2 shows a closer view of anillustrative environment 10 for prioritizing the processing of multiple video streams according to an embodiment of the invention. To this extent,environment 10 includes acomputer system 12 that can perform the process described herein in order to detect irregular checkout activities. In particular,computer system 12 is shown including acomputing device 14 that comprises anintelligent switching program 30, which makescomputing device 14 operable for prioritizing the processing of multiple video streams, by performing the process described herein. -
Computing device 14 is shown including aprocessor 20, amemory 22A, an input/output (I/O) interface 24, and abus 26. Further,computing device 14 is shown in communication with an external I/O device/resource 28 and astorage device 22B. In general,processor 20 executes program code, such asintelligent switching program 30, which is stored in a storage system, such asmemory 22A and/orstorage device 22B. While executing program code,processor 20 can read and/or write data, such asdata 36 to/frommemory 22A,storage device 22B, and/or I/O interface 24.Bus 26 provides a communications link between each of the components incomputing device 14. I/O device 28 can comprise any device that transfers information between auser 16 andcomputing device 14 and/ordigital video input transaction data input computing device 14. To this extent, I/O device 28 can comprise a user I/O device to enable anindividual user 16 to interact withcomputing device 14 and/or a communications device to enable an element, such asdigital video input transaction data input computing device 14 using any type of communications link. - In any event,
computing device 14 can comprise any general purpose computing article of manufacture capable of executing program code installed thereon. However, it is understood that computingdevice 14 andintelligent switching program 30 are only representative of various possible equivalent computing devices that may perform the process described herein. To this extent, in other embodiments, the functionality provided by computingdevice 14 andintelligent switching program 30 can be implemented by a computing article of manufacture that includes any combination of general and/or specific purpose hardware and/or program code. In each embodiment, the program code and hardware can be created using standard programming and engineering techniques, respectively. Such standard programming and engineering techniques include an open architecture to allow integration of processing from different retailers. Such an open architecture includes cloud computing. - Similarly,
computer system 12 is only illustrative of various types of computer systems for implementing aspects of the invention. For example, in one embodiment,computer system 12 comprises two or more computing devices that communicate over any type of communications link, such as a network, a shared memory, or the like, to perform the process described herein. Further, while performing the process described herein, one or more computing devices incomputer system 12 can communicate with one or more other computing devices external tocomputer system 12 using any type of communications link. In either case, the communications link can comprise any combination of various types of wired and/or wireless links; comprise any combination of one or more types of networks; and/or utilize any combination of various types of transmission techniques and protocols. - As discussed herein,
intelligent switching program 30 enablescomputer system 12 to detect irregular checkout activities. To this extent,intelligent switching program 30 is shown including aprescheduling module 32, apreprocessing module 34, a prioritizingmodule 36, aprocessing module 37, acleanup module 38, and anarchiving module 39. Operation of each of these modules is discussed further herein. However, it is understood that some of the various modules shown inFIG. 2 can be implemented independently, combined, and/or stored in memory of one or more separate computing devices that are included incomputer system 12. Further, it is understood that some of the modules and/or functionality may not be implemented, or additional modules and/or functionality may be included as part ofcomputer system 12. -
FIG. 3 illustrates a system diagram of an exemplary video transaction intelligent switching program 30 (FIG. 2 ). The present invention contemplates a plurality of lanes in one or more retail stores. This non-limiting example depicts a system prioritizing the processing of multiple video streams installed in a retail store. To this extent, the retail store maintains an arbitrary number of lanes. Cameras are installed to capture transaction activities at each lane. Transaction data (e.g., prices, item numbers, quantities, etc.) is sent along with video capture of each transaction. The transaction includes both the transaction data and the video stream. This non-limiting example assumes that there are N lanes (lane 1 to lane N) to be processed as determined by a prescheduling module 32 (FIG. 2 ). In the prescheduling module, aprescheduling filter 111 is installed forlane 1. Likewise, anotherfilter 112 is installed forlane 2, and filter 113 is installed for lane N-1, and filter 114 for lane N. - The prescheduling filters determine whether a transaction from a particular lane should be monitored based on whether the lane is open. All transactions from lanes are sent to the preprocessing module 34 (
FIG. 2 ). Thepreprocessing module 34 organizes the transactions such that each transaction is isolated and given a unique ID. All transactions are then presented to the prioritizingmodule 36. The prioritizingmodule 36 uses predetermined rules, which are also capable of being dynamically updated, to calculate a priority score for each transaction. - The prioritizing
module 36 maintains atransaction priority queue 140, which contains transactions with priority scores. Transactions are listed in thetransaction priority queue 140 in the order of their priority score. Theprocessing module 37 processes transactions with the highest priority score first from thetransaction priority queue 140. Theprocessing module 37 contains the relatively computationally-intensive irregular activity detection software to analyze each transaction to discover whether irregular activity has occurred for that particular transaction. As a transaction is processed by theprocessing module 37, the transaction unit for that transaction is moved to anarchival queue 170. - A
cleanup module 38 monitors thetransaction priority queue 140 at regular time intervals. If a transaction has been in thetransaction priority queue 140 for more than a predetermined amount of time (e.g., 10 seconds) and the priority score for the transaction is low, thecleanup module 38 will move the transaction to thearchival queue 170. - The
archiving module 39 processes transaction units in thearchival queue 170 by moving the transaction units in thearchival queue 170 topersistent storage 190. Frompersistent storage 190, data can be extracted to form part of prioritizingrules 195.Human operator 16 can also provide prioritizing rules 195. Prioritizingrules 195 are used by the prioritizingmodule 36 to prioritize transactions. - According to an embodiment of the invention, when the
processing module 37 has unused capacity (e.g., late at night when there are few customers or when the store is closed), unprocessed transactions from thepersistent storage 190 can be sent back to the prioritizingmodule 36 to be reprocessed -
FIGS. 4A and 4B illustrate two stages of priority setting among transactions.FIG. 4A illustrates a first stage of prioritizing transactions. In this first stage, transactions from Lanes 1-3 are sent to the prioritizingmodule 36. Based on the prioritizing rules provided byhuman operator 16 and the characteristics of each transaction, the prioritizingmodule 36 prioritizes transactions in the order of T1 to TN with T1 having the highest priority. - For example, T1 from
Lane 1 has the highest priority because thecashier operating Lane 1 has been flagged by the manager. T2 fromLane 2 is given a high priority because the transaction contains three voided items. T3 fromLane 3 is also given a high priority because the entire transaction is voided. However, the priority given to T2 is higher than that of T3 because three voided items in a single transaction is considered a more irregular activity than voiding an entire transaction, according to the system rule design. T4 fromLane 2 is given a high priority because the transaction contains unusually long durations between item scans. Long durations between scans is a possible cue that the cashier is moving items from the entry belt to the exit belt without entering the items into the transaction between items that are being entered into the transaction (i.e., the items are bagged and taken away by the customer without being purchased). There are many other reasons for long durations between items (e.g., the cashier stops to bag items), so T4 is given a lower priority than T1-T3. In comparison, TN fromLane 2 is given low priority because it is a seemingly ordinary transaction. -
FIG. 4B illustrates a second stage of prioritizing transactions. In this second stage, the prioritizing rules have been updated with the transaction data from the first stage. In the first stage, the cashier fromLane 2 issued multiple suspicious transactions. As a result, the prioritizing rules were updated based on this information. - In the second stage as illustrated by
FIG. 4B , new transactions T1 to TN are processed by the prioritizingmodule 36. T1 fromLane 2 is given top priority because the first stage showed multiple suspicious transactions from the same cashier and a large number of high value items. T2 fromLane 3 is given a high priority because the same cashier fromLane 3 had two managerial overwrites issued. T3 fromLane 3 is given high priority because the same cashier is considered suspicious. T4 is given high priority because a customer pays cash. Paying in cash means that the identity of buyer is not recorded as it would be, for example, in a credit card transaction, so there is a correlation between cash purchases and fraud. However, the correlation is not very strong relative to the items that are prioritized ahead of it. TN is given low priority because a different cashier now works atLane 1 and the cashier is not flagged as suspicious. In addition, the transaction TN is an ordinary, non-suspicious transaction. -
FIG. 5 illustrates a flowchart for exemplary steps of assigning priorities for transaction units. Instep 501, the intelligent switching program takes initial input for assigning priorities. Instep 502, the intelligent switching program initiates a statistical sampling model to process transactional data and video stream, which is combined into a transaction unit. Instep 503, the intelligent switching program analyzes features of each transaction unit. The features includes but are not limited to: activity level at each lane, e.g., can be obtained by analyzing the object detection and tracking algorithms; volume of transactions in terms of both number of transactions and monetary amounts; and results of irregular activity detections in the near history which is also used to update the historical data to affect future transaction priority ordering. Instep 504, the intelligent system uses statistical models (e.g., Gaussian, Poisson, exponential, uniform, etc.) to determine correlations between features of the transaction units. Instep 505, each transaction unit is given a priority score based on analysis results and placed in the transaction priority queue. -
FIG. 6 illustrates a flowchart for exemplary steps of processing transactions according to the present invention. Instep 601, the monitoring system preprocesses video capture and transaction data and turns them into identifiable individual transaction units. Instep 602, the prioritizing system prioritizes the individual transaction units based on priority rules. Instep 603, the system determines whether a transaction unit has high enough priority to be processed. If the transaction unit has relatively high priority, the transaction is processed instep 604. If the transaction unit does not have high priority instep 603, the transaction unit is archived directly instep 605. After the transaction unit is processed instep 604, irregular activities are captured and reported instep 606. Processed transactions fromstep 604 are also archived instep 605. An analysis of all transactions fromstep 605 provides the basis for updating prioritizing rules instep 607.
Claims (24)
1. A method, comprising:
prioritizing by a computer system processor each transaction unit of a plurality of individual transaction units into a prioritized processing order, wherein each of the individual transaction units comprise transaction data and video data corresponding to an item purchased by a customer at one of a plurality of different checkout lanes, and wherein the prioritizing is a function of:
a lane priority value of a respective one of the different checkout lanes that the transaction unit video data and transaction data is captured from for each of the individual transaction units, wherein each of the different checkout lanes has a different lane priority value; and
a transaction unit type priority value of a type of transaction unit indicated by the transaction data of each of the individual transaction units, wherein the transaction unit type is selected from a plurality of different transaction unit types that each have a different transaction unit type priority value; and
processing by the processor the individual transaction units in the prioritized processing order to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed individual transaction units.
2. The method of claim 1 , wherein the different transaction unit types comprise:
a first transaction unit type comprising at least one voided item within a transaction;
a second transaction unit type comprising a voiding of all items within a single transaction; and
a third transaction unit type comprising a long time duration between item scans in a single transaction.
3. The method of claim 2 , further comprising:
the processor dynamically updating and increasing the lane priority value of a first of the different checkout lanes as a function of the processing of the individual transaction units in the prioritized processing order automatically detecting irregular activities within processed transaction unit video and the transaction data captured from the first checkout lane; and
subsequently determining processing priority by the processor for each transaction unit of the individual transaction units captured from the different checkout lanes as a function of the updated lane priority value of the first checkout lane.
4. The method of claim 3 , wherein the determining processing priority for each transaction unit comprises using one or more Gaussian, Poisson, exponential, or uniform statistical models to determine correlations between features of the transaction unit.
5. The method of claim 4 , wherein the step of the processor processing the individual transaction units in the prioritized processing order to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed individual transaction units further comprises:
processing a high priority fraction of a total of the prioritized individual transaction units in the prioritized processing order; and
archiving by the processor a low priority remainder fraction of the total of the individual transaction units that each has a lower priority than the high priority fraction individual transaction units within the prioritized processing order.
6. The method of claim 5 , wherein the step of prioritizing the individual transaction units further comprises placing the transactions units in a transaction priority queue in an order of relative priority; and
wherein the step of the processor archiving the low priority remainder fraction of the total of the individual transaction units further comprises moving the low priority remainder fraction transaction units from the transaction priority queue to an archival queue in an order of relative priority.
7. The method of claim 6 , further comprising the processor moving unprocessed transaction units from the transaction priority queue to the archival queue at regular intervals.
8. The method of claim 7 , further comprising the processor processing the low priority remainder fraction individual transaction units archived in the archival queue in order of their relative queued priority to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed transaction units when the processor has unused capacity.
9. The method of claim 8 , further comprising:
obtaining by the processor streams of video and transaction data captured from each of the plurality of different checkout lanes; and
combining by the processor the streams of video and transaction data for each respective one of the different checkout lanes into the individual transaction units so that each comprises transaction video corresponding to a set of items purchased by a single customer at one of the different checkout lanes in a single span of time.
10. A method for providing a service for automatically detecting irregular activities indicated by the transaction unit video and transaction data, the method comprising:
integrating computer-readable program code into a computer system comprising a processor, a computer readable memory and a computer readable tangible storage device, wherein the computer readable program code is embodied on the computer readable tangible storage device and comprises instructions that, when executed by the processor via the computer readable memory, cause the processor to:
prioritize each transaction unit of a plurality of individual transaction units into a prioritized processing order, wherein each of the individual transaction units comprise transaction data and video data corresponding to an item purchased by a customer at one of a plurality of different checkout lanes, and wherein the prioritizing is a function of:
a lane priority value of a respective one of the different checkout lanes that the transaction unit video data and transaction data is captured from for each of the individual transaction units, wherein each of the different checkout lanes has a different lane priority value; and
a transaction unit type priority value of a type of transaction unit indicated by the transaction data of each of the individual transaction units, wherein the transaction unit type is selected from a plurality of different transaction unit types that each have a different transaction unit type priority value; and
process the individual transaction units in the prioritized processing order to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed individual transaction units.
11. The method of claim 12 , wherein the processor, when executing the program instructions stored on the tangible computer-readable storage device via the computer readable memory, further:
dynamically updates and increases the lane priority value of a first of the different checkout lanes as a function of the processing of the individual transaction units in the prioritized processing order automatically detecting irregular activities within processed transaction unit video and the transaction data captured from the first checkout lane; and
subsequently determines processing priority for each transaction unit of the individual transaction units captured from the different checkout lanes as a function of the updated lane priority value of the first checkout lane.
12. The method of claim 11 , wherein the processor, when executing the program instructions stored on the tangible computer-readable storage device via the computer readable memory, further archives a low priority remainder fraction of a total of the individual transaction units in the prioritized processing order that each have a lower priority than a high priority fraction of the prioritized individual transaction units.
13. The method of claim 12 , wherein the processor, when executing the program instructions stored on the tangible computer-readable storage device via the computer readable memory, further processes the archived low priority remainder fraction individual transaction units in order of their relative queued priority to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed transaction units when the processor has unused capacity.
14. The method of claim 13 , wherein the processor, when executing the program instructions stored on the tangible computer-readable storage device via the computer readable memory, further:
obtains streams of video and transaction data captured from each of the plurality of different checkout lanes; and
combines the streams of video and transaction data for each respective one of the different checkout lanes into the individual transaction units so that each comprises transaction video corresponding to a set of items purchased by a single customer at one of the different checkout lanes in a single span of time.
15. A system, comprising:
a processor in communication with a computer readable memory and a tangible computer-readable storage device;
wherein the processor, when executing program instructions stored on the tangible computer-readable storage device via the computer readable memory:
prioritizes each transaction unit of a plurality of individual transaction units into a prioritized processing order, wherein each of the individual transaction units comprise transaction data and video data corresponding to an item purchased by a customer at one of a plurality of different checkout lanes, and wherein the prioritizing is a function of:
a lane priority value of a respective one of the different checkout lanes that the transaction unit video data and transaction data is captured from for each of the individual transaction units, wherein each of the different checkout lanes has a different lane priority value; and
a transaction unit type priority value of a type of transaction unit indicated by the transaction data of each of the individual transaction units, wherein the transaction unit type is selected from a plurality of different transaction unit types that each have a different transaction unit type priority value; and
processes the individual transaction units in the prioritized processing order to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed individual transaction units.
16. The system of claim 15 , wherein the processor, when executing the program instructions stored on the computer-readable storage device via the computer readable memory, further:
dynamically updates and increases the lane priority value of a first of the different checkout lanes as a function of the processing of the individual transaction units in the prioritized processing order automatically detecting irregular activities within processed transaction unit video and the transaction data captured from the first checkout lane; and
subsequently determines processing priority for each transaction unit of the individual transaction units captured from the different checkout lanes as a function of the updated lane priority value of the first checkout lane.
17. The system of claim 16 , wherein the processor, when executing the program instructions stored on the computer-readable storage device via the computer readable memory, further archives a low priority remainder fraction of a total of the individual transaction units in the prioritized processing order that each have a lower priority than a high priority fraction of the prioritized individual transaction units.
18. The system of claim 17 , wherein the processor, when executing the program instructions stored on the computer-readable storage device via the computer readable memory, further processes the archived low priority remainder fraction individual transaction units in order of their relative queued priority to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed transaction units, when the system has unused capacity.
19. The system of claim 18 , wherein the processor, when executing the program instructions stored on the computer-readable storage device via the computer readable memory, further:
obtains streams of video and transaction data captured from each of the plurality of different checkout lanes; and
combines the streams of video and transaction data for each respective one of the different checkout lanes into the individual transaction units so that each comprises transaction video corresponding to a set of items purchased by a single customer at one of the different checkout lanes in a single span of time.
20. An article of manufacture, comprising:
a computer readable tangible storage device having computer readable program code embodied therewith, the computer readable program code comprising instructions that, when executed by a computer processor, cause the computer processor to:
prioritize each transaction unit of a plurality of individual transaction units into a prioritized processing order, wherein each of the individual transaction units comprise transaction data and video data corresponding to an item purchased by a customer at one of a plurality of different checkout lanes, and wherein the prioritizing is a function of:
a lane priority value of a respective one of the different checkout lanes that the transaction unit video data and transaction data is captured from for each of the individual transaction units, wherein each of the different checkout lanes has a different lane priority value; and
a transaction unit type priority value of a type of transaction unit indicated by the transaction data of each of the individual transaction units, wherein the transaction unit type is selected from a plurality of different transaction unit types that each have a different transaction unit type priority value; and
process the individual transaction units in the prioritized processing order to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed individual transaction units.
21. The article of manufacture of claim 20 , wherein the computer readable program code instructions, when executed by the computer processor, further cause the processor to:
dynamically update and increase the lane priority value of a first of the different checkout lanes as a function of the processing of the individual transaction units in the prioritized processing order automatically detecting irregular activities within processed transaction unit video and the transaction data captured from the first checkout lane; and
subsequently determine processing priority for each transaction unit of the individual transaction units captured from the different checkout lanes as a function of the updated lane priority value of the first checkout lane.
22. The article of manufacture of claim 21 , wherein the computer readable program code instructions, when executed by the computer processor, further cause the processor to archive a low priority remainder fraction of a total of the individual transaction units in the prioritized processing order that each have a lower priority than a high priority fraction of the prioritized individual transaction units.
23. The article of manufacture of claim 22 , wherein the computer readable program code instructions, when executed by the computer processor, further cause the processor to process the archived low priority remainder fraction individual transaction units in order of their relative queued priority to automatically detect irregular activities indicated by the transaction unit video and the transaction data of the processed transaction units, when the processor has unused capacity.
24. The article of manufacture of claim 23 , wherein the computer readable program code instructions, when executed by the computer processor, further cause the processor to:
obtain streams of video and transaction data captured from each of the plurality of different checkout lanes; and
combine the streams of video and transaction data for each respective one of the different checkout lanes into the individual transaction units so that each comprises transaction video corresponding to a set of items purchased by a single customer at one of the different checkout lanes in a single span of time.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/559,996 US20120293661A1 (en) | 2010-02-01 | 2012-07-27 | Optimizing video stream processing |
US14/022,324 US9197868B2 (en) | 2010-02-01 | 2013-09-10 | Optimizing video stream processing |
US14/884,927 US9569672B2 (en) | 2010-02-01 | 2015-10-16 | Optimizing video stream processing |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/697,530 US8259175B2 (en) | 2010-02-01 | 2010-02-01 | Optimizing video stream processing |
US13/559,996 US20120293661A1 (en) | 2010-02-01 | 2012-07-27 | Optimizing video stream processing |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/697,530 Continuation US8259175B2 (en) | 2010-02-01 | 2010-02-01 | Optimizing video stream processing |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/022,324 Continuation US9197868B2 (en) | 2010-02-01 | 2013-09-10 | Optimizing video stream processing |
Publications (1)
Publication Number | Publication Date |
---|---|
US20120293661A1 true US20120293661A1 (en) | 2012-11-22 |
Family
ID=44319894
Family Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/697,530 Expired - Fee Related US8259175B2 (en) | 2010-02-01 | 2010-02-01 | Optimizing video stream processing |
US13/559,996 Abandoned US20120293661A1 (en) | 2010-02-01 | 2012-07-27 | Optimizing video stream processing |
US14/022,324 Active 2030-10-06 US9197868B2 (en) | 2010-02-01 | 2013-09-10 | Optimizing video stream processing |
US14/884,927 Active US9569672B2 (en) | 2010-02-01 | 2015-10-16 | Optimizing video stream processing |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/697,530 Expired - Fee Related US8259175B2 (en) | 2010-02-01 | 2010-02-01 | Optimizing video stream processing |
Family Applications After (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/022,324 Active 2030-10-06 US9197868B2 (en) | 2010-02-01 | 2013-09-10 | Optimizing video stream processing |
US14/884,927 Active US9569672B2 (en) | 2010-02-01 | 2015-10-16 | Optimizing video stream processing |
Country Status (6)
Country | Link |
---|---|
US (4) | US8259175B2 (en) |
JP (1) | JP5674212B2 (en) |
CN (1) | CN102714713A (en) |
DE (1) | DE112011100093B4 (en) |
GB (1) | GB2489831B (en) |
WO (1) | WO2011092044A2 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110149073A1 (en) * | 2007-11-06 | 2011-06-23 | Zenith Asset Management Limited | method of monitoring product identification and apparatus therefor |
US20140214568A1 (en) * | 2013-01-29 | 2014-07-31 | Wal-Mart Stores, Inc. | Retail loss prevention using biometric data |
US9603019B1 (en) | 2014-03-28 | 2017-03-21 | Confia Systems, Inc. | Secure and anonymized authentication |
US9602292B2 (en) | 2015-07-25 | 2017-03-21 | Confia Systems, Inc. | Device-level authentication with unique device identifiers |
US10484359B2 (en) | 2015-07-25 | 2019-11-19 | Confia Systems, Inc. | Device-level authentication with unique device identifiers |
Families Citing this family (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8259175B2 (en) * | 2010-02-01 | 2012-09-04 | International Business Machines Corporation | Optimizing video stream processing |
US8594482B2 (en) | 2010-05-13 | 2013-11-26 | International Business Machines Corporation | Auditing video analytics through essence generation |
US9569938B1 (en) * | 2010-12-12 | 2017-02-14 | Verint Americas Inc. | Video content analysis using point of sale data |
CA2835719C (en) * | 2011-05-12 | 2019-12-31 | Solink Corporation | Video analytics system |
IES86318B2 (en) | 2012-08-15 | 2013-12-04 | Everseen | Intelligent retail manager |
US11170331B2 (en) | 2012-08-15 | 2021-11-09 | Everseen Limited | Virtual management system data processing unit and method with rules and alerts |
US20140180848A1 (en) * | 2012-12-20 | 2014-06-26 | Wal-Mart Stores, Inc. | Estimating Point Of Sale Wait Times |
JP6219101B2 (en) * | 2013-08-29 | 2017-10-25 | 株式会社日立製作所 | Video surveillance system, video surveillance method, video surveillance system construction method |
KR20170070649A (en) * | 2015-12-14 | 2017-06-22 | 에스프린팅솔루션 주식회사 | Image forming apparuatus, cloud server, image forming system, and method for setting of connection with image forming apparatus |
GB2549970A (en) * | 2016-05-04 | 2017-11-08 | Canon Europa Nv | Method and apparatus for generating a composite video from a pluarity of videos without transcoding |
US20180158063A1 (en) * | 2016-12-05 | 2018-06-07 | RetailNext, Inc. | Point-of-sale fraud detection using video data and statistical evaluations of human behavior |
US11675617B2 (en) * | 2018-03-21 | 2023-06-13 | Toshiba Global Commerce Solutions Holdings Corporation | Sensor-enabled prioritization of processing task requests in an environment |
US11062315B2 (en) * | 2018-04-25 | 2021-07-13 | At&T Intellectual Property I, L.P. | Fraud as a service |
US11651206B2 (en) * | 2018-06-27 | 2023-05-16 | International Business Machines Corporation | Multiscale feature representations for object recognition and detection |
CN110087033A (en) * | 2019-04-24 | 2019-08-02 | 北京旷视科技有限公司 | Processing system for video and method, video processing equipment and medium |
CN112580412A (en) * | 2019-09-30 | 2021-03-30 | 百度(美国)有限责任公司 | Commodity identification method and device |
US10607080B1 (en) * | 2019-10-25 | 2020-03-31 | 7-Eleven, Inc. | Feedback and training for a machine learning algorithm configured to determine customer purchases during a shopping session at a physical store |
CN111723702B (en) * | 2020-06-08 | 2024-02-27 | 苏州工业职业技术学院 | Data monitoring method, device and payment system |
CN114222162A (en) * | 2021-12-07 | 2022-03-22 | 浙江大华技术股份有限公司 | Video processing method, video processing device, computer equipment and storage medium |
WO2023237919A1 (en) * | 2022-06-07 | 2023-12-14 | Telefonaktiebolaget Lm Ericsson (Publ) | Cascade stages priority-based processing |
CN117473504B (en) * | 2023-12-27 | 2024-03-01 | 北京中科卓信软件测评技术中心 | Channel blocking detection method and device based on channel operation priority Go program |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5494136A (en) * | 1993-08-05 | 1996-02-27 | Humble; David R. | Integrated automated retail checkout terminal |
US5883968A (en) * | 1994-07-05 | 1999-03-16 | Aw Computer Systems, Inc. | System and methods for preventing fraud in retail environments, including the detection of empty and non-empty shopping carts |
US20040059614A1 (en) * | 2002-08-29 | 2004-03-25 | Brown Michael Wayne | Customer checkout system |
US20050102183A1 (en) * | 2003-11-12 | 2005-05-12 | General Electric Company | Monitoring system and method based on information prior to the point of sale |
US6974083B1 (en) * | 2004-07-23 | 2005-12-13 | Symbol Technologies, Inc. | Point-of-transaction workstation for electro-optically reading one-dimensional indicia, including image capture of two-dimensional targets |
US20060243798A1 (en) * | 2004-06-21 | 2006-11-02 | Malay Kundu | Method and apparatus for detecting suspicious activity using video analysis |
US7229012B1 (en) * | 1998-10-09 | 2007-06-12 | Diebold, Incorporated | System and method for capturing and searching image data associated with transactions |
US20070182818A1 (en) * | 2005-09-02 | 2007-08-09 | Buehler Christopher J | Object tracking and alerts |
US7416118B2 (en) * | 2004-05-14 | 2008-08-26 | Digital Site Management, Llc | Point-of-sale transaction recording system |
US20080208698A1 (en) * | 2007-02-26 | 2008-08-28 | Quentin Olson | Point of sale video server processing system |
US7516888B1 (en) * | 2004-06-21 | 2009-04-14 | Stoplift, Inc. | Method and apparatus for auditing transaction activity in retail and other environments using visual recognition |
US20090234683A1 (en) * | 2000-06-30 | 2009-09-17 | Russell Anderson | Detecting and Measuring Risk with Predictive Models Using Content Mining |
US20100059589A1 (en) * | 2008-09-05 | 2010-03-11 | Luis Goncalves | System and method for preventing cashier and customer fraud at retail checkout |
US20100114623A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Using detailed process information at a point of sale |
US7721336B1 (en) * | 2001-03-15 | 2010-05-18 | Brighterion, Inc. | Systems and methods for dynamic detection and prevention of electronic fraud |
US20100134624A1 (en) * | 2008-10-31 | 2010-06-03 | International Business Machines Corporation | Detecting primitive events at checkout |
US20100161526A1 (en) * | 2008-12-19 | 2010-06-24 | The Mitre Corporation | Ranking With Learned Rules |
US7965184B1 (en) * | 2008-06-16 | 2011-06-21 | Bank Of America Corporation | Cash handling facility management |
US20110188701A1 (en) * | 2010-02-01 | 2011-08-04 | International Business Machines Corporation | Optimizing video stream processing |
Family Cites Families (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4630110A (en) * | 1984-02-15 | 1986-12-16 | Supervision Control Systems, Inc. | Surveillance system |
EP0664034B1 (en) | 1992-10-09 | 2001-07-11 | Catalina Marketing International, Inc. | Method and apparatus for filtering point-of-sale data |
JPH09115028A (en) * | 1995-10-16 | 1997-05-02 | Oki Electric Ind Co Ltd | Monitoring camera photographing method for cs corner |
JPH09259381A (en) * | 1996-03-22 | 1997-10-03 | Kyocera Corp | Remote monitor device |
US7015945B1 (en) * | 1996-07-10 | 2006-03-21 | Visilinx Inc. | Video surveillance system and method |
US7209891B1 (en) * | 1999-02-08 | 2007-04-24 | Ncr Corporation | Method and apparatus for operating a configurable remote supervisor terminal of a self-service retail checkout system |
US6571218B1 (en) * | 1999-04-14 | 2003-05-27 | Ncr Corporation | Remote approval system and methods for use in network of retail checkout terminals |
US20050146605A1 (en) * | 2000-10-24 | 2005-07-07 | Lipton Alan J. | Video surveillance system employing video primitives |
US20020170782A1 (en) * | 2001-05-17 | 2002-11-21 | Ncr Corporation | Scalable self-checkout system |
US20060190960A1 (en) | 2005-02-14 | 2006-08-24 | Barker Geoffrey T | System and method for incorporating video analytics in a monitoring network |
JP5054670B2 (en) * | 2005-03-29 | 2012-10-24 | ストップリフト インコーポレイテッド | Method and apparatus for detecting suspicious behavior using video analysis |
US20090201372A1 (en) * | 2006-02-13 | 2009-08-13 | Fraudhalt, Ltd. | Method and apparatus for integrated atm surveillance |
WO2007124138A2 (en) * | 2006-04-18 | 2007-11-01 | Sorensen Associates Inc | Still image queue analysis system and method |
US7925536B2 (en) * | 2006-05-25 | 2011-04-12 | Objectvideo, Inc. | Intelligent video verification of point of sale (POS) transactions |
TW200822751A (en) * | 2006-07-14 | 2008-05-16 | Objectvideo Inc | Video analytics for retail business process monitoring |
US20080162952A1 (en) * | 2007-01-03 | 2008-07-03 | John David Landers | Managing power usage in a data processing system by changing the clock speed of a processing unit |
WO2008092255A1 (en) * | 2007-01-30 | 2008-08-07 | March Networks Corporation | Method and system for task-based video analytics processing |
EP1956460B1 (en) | 2007-02-08 | 2008-10-29 | Nordiq Göteborg AG | Heating system control based on required heating power |
WO2008134562A2 (en) * | 2007-04-27 | 2008-11-06 | Nielsen Media Research, Inc. | Methods and apparatus to monitor in-store media and consumer traffic related to retail environments |
US20080290182A1 (en) * | 2007-05-23 | 2008-11-27 | International Business Machines Corporation | System and method for calculating wait-time for checkout |
US8107676B2 (en) * | 2007-07-30 | 2012-01-31 | International Business Machines Corporation | Line length estimation |
US20090076922A1 (en) * | 2007-09-19 | 2009-03-19 | De Gruil Rasmus | Method,device and system for improving the utilization of customer operated terminals |
US20090327054A1 (en) * | 2008-06-27 | 2009-12-31 | Microsoft Corporation | Personal reputation system based on social networking |
US8484297B2 (en) * | 2008-07-31 | 2013-07-09 | Palo Alto Research Center Incorporated | Method for collaboratively tagging and highlighting electronic documents |
US8010602B2 (en) * | 2008-08-28 | 2011-08-30 | Microsoft Corporation | Leveraging communications to identify social network friends |
US8180765B2 (en) * | 2009-06-15 | 2012-05-15 | Telefonaktiebolaget L M Ericsson (Publ) | Device and method for selecting at least one media for recommendation to a user |
-
2010
- 2010-02-01 US US12/697,530 patent/US8259175B2/en not_active Expired - Fee Related
-
2011
- 2011-01-05 GB GB1206960.5A patent/GB2489831B/en not_active Expired - Fee Related
- 2011-01-05 DE DE112011100093.6T patent/DE112011100093B4/en active Active
- 2011-01-05 WO PCT/EP2011/050098 patent/WO2011092044A2/en active Application Filing
- 2011-01-05 JP JP2012550379A patent/JP5674212B2/en not_active Expired - Fee Related
- 2011-01-05 CN CN2011800066022A patent/CN102714713A/en active Pending
-
2012
- 2012-07-27 US US13/559,996 patent/US20120293661A1/en not_active Abandoned
-
2013
- 2013-09-10 US US14/022,324 patent/US9197868B2/en active Active
-
2015
- 2015-10-16 US US14/884,927 patent/US9569672B2/en active Active
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5494136A (en) * | 1993-08-05 | 1996-02-27 | Humble; David R. | Integrated automated retail checkout terminal |
US5883968A (en) * | 1994-07-05 | 1999-03-16 | Aw Computer Systems, Inc. | System and methods for preventing fraud in retail environments, including the detection of empty and non-empty shopping carts |
US7229012B1 (en) * | 1998-10-09 | 2007-06-12 | Diebold, Incorporated | System and method for capturing and searching image data associated with transactions |
US20090234683A1 (en) * | 2000-06-30 | 2009-09-17 | Russell Anderson | Detecting and Measuring Risk with Predictive Models Using Content Mining |
US7721336B1 (en) * | 2001-03-15 | 2010-05-18 | Brighterion, Inc. | Systems and methods for dynamic detection and prevention of electronic fraud |
US20040059614A1 (en) * | 2002-08-29 | 2004-03-25 | Brown Michael Wayne | Customer checkout system |
US20050102183A1 (en) * | 2003-11-12 | 2005-05-12 | General Electric Company | Monitoring system and method based on information prior to the point of sale |
US7416118B2 (en) * | 2004-05-14 | 2008-08-26 | Digital Site Management, Llc | Point-of-sale transaction recording system |
US7516888B1 (en) * | 2004-06-21 | 2009-04-14 | Stoplift, Inc. | Method and apparatus for auditing transaction activity in retail and other environments using visual recognition |
US20090226099A1 (en) * | 2004-06-21 | 2009-09-10 | Malay Kundu | Method and apparatus for auditing transaction activity in retail and other environments using visual recognition |
US20060243798A1 (en) * | 2004-06-21 | 2006-11-02 | Malay Kundu | Method and apparatus for detecting suspicious activity using video analysis |
US7631808B2 (en) * | 2004-06-21 | 2009-12-15 | Stoplift, Inc. | Method and apparatus for detecting suspicious activity using video analysis |
US6974083B1 (en) * | 2004-07-23 | 2005-12-13 | Symbol Technologies, Inc. | Point-of-transaction workstation for electro-optically reading one-dimensional indicia, including image capture of two-dimensional targets |
US20070182818A1 (en) * | 2005-09-02 | 2007-08-09 | Buehler Christopher J | Object tracking and alerts |
US20080208698A1 (en) * | 2007-02-26 | 2008-08-28 | Quentin Olson | Point of sale video server processing system |
US7965184B1 (en) * | 2008-06-16 | 2011-06-21 | Bank Of America Corporation | Cash handling facility management |
US20100059589A1 (en) * | 2008-09-05 | 2010-03-11 | Luis Goncalves | System and method for preventing cashier and customer fraud at retail checkout |
US20100114623A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Using detailed process information at a point of sale |
US7962365B2 (en) * | 2008-10-31 | 2011-06-14 | International Business Machines Corporation | Using detailed process information at a point of sale |
US20100134624A1 (en) * | 2008-10-31 | 2010-06-03 | International Business Machines Corporation | Detecting primitive events at checkout |
US20100161526A1 (en) * | 2008-12-19 | 2010-06-24 | The Mitre Corporation | Ranking With Learned Rules |
US20110188701A1 (en) * | 2010-02-01 | 2011-08-04 | International Business Machines Corporation | Optimizing video stream processing |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110149073A1 (en) * | 2007-11-06 | 2011-06-23 | Zenith Asset Management Limited | method of monitoring product identification and apparatus therefor |
US20140214568A1 (en) * | 2013-01-29 | 2014-07-31 | Wal-Mart Stores, Inc. | Retail loss prevention using biometric data |
US8874471B2 (en) * | 2013-01-29 | 2014-10-28 | Wal-Mart Stores, Inc. | Retail loss prevention using biometric data |
US9603019B1 (en) | 2014-03-28 | 2017-03-21 | Confia Systems, Inc. | Secure and anonymized authentication |
US9602292B2 (en) | 2015-07-25 | 2017-03-21 | Confia Systems, Inc. | Device-level authentication with unique device identifiers |
US10484359B2 (en) | 2015-07-25 | 2019-11-19 | Confia Systems, Inc. | Device-level authentication with unique device identifiers |
Also Published As
Publication number | Publication date |
---|---|
US20160034766A1 (en) | 2016-02-04 |
US8259175B2 (en) | 2012-09-04 |
US9197868B2 (en) | 2015-11-24 |
CN102714713A (en) | 2012-10-03 |
GB2489831B (en) | 2016-04-20 |
WO2011092044A2 (en) | 2011-08-04 |
JP2013518334A (en) | 2013-05-20 |
US9569672B2 (en) | 2017-02-14 |
DE112011100093B4 (en) | 2021-04-15 |
GB201206960D0 (en) | 2012-06-06 |
JP5674212B2 (en) | 2015-02-25 |
GB2489831A (en) | 2012-10-10 |
DE112011100093T5 (en) | 2012-10-11 |
US20140009620A1 (en) | 2014-01-09 |
WO2011092044A3 (en) | 2012-03-01 |
US20110188701A1 (en) | 2011-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9569672B2 (en) | Optimizing video stream processing | |
US10068136B2 (en) | Event detection based on video metadata | |
US9549156B2 (en) | Dynamic allocation of video resources | |
US9003030B2 (en) | Detecting relative crowd density via client devices | |
US9846811B2 (en) | System and method for video-based determination of queue configuration parameters | |
US11669738B2 (en) | Context-aided machine vision | |
CN105306277A (en) | Message scheduling method and message scheduling device for message queues | |
JP7146759B2 (en) | Optimizing human and non-human resources in the retail environment | |
CN107169861A (en) | Site sales service system and method | |
CN112269811A (en) | IT capacity prediction method and system based on traffic | |
CN109146128B (en) | Service data processing method and device and server | |
CN114971449A (en) | Article inventory management method, apparatus, electronic device and medium | |
CN111754218A (en) | Payment mode recommendation method and device | |
CN108681745A (en) | The recognition methods of exception information and device, storage medium, electronic device | |
CN114372735A (en) | Method and device for determining buffer stock quantity data in logistics supply chain | |
Rigter et al. | Optimal admission control for multiclass queues with time-varying arrival rates via state abstraction | |
RU2785327C1 (en) | Computer vision system in retail | |
KR102644685B1 (en) | Review reliability validation device and method of thereof | |
US20230095391A1 (en) | Self-service terminal (sst) management assistance | |
US20230419201A1 (en) | Systems and methods for service location optimization | |
Thakur et al. | Challenges and Opportunities Presented by the Internet of Things (IoTs) in the Hospitality Industry | |
WO2021024348A1 (en) | IoT DEVICE MANAGEMENT APPARATUS, IoT DEVICE MANAGEMENT METHOD, AND PROGRAM | |
CN115080833A (en) | Information flow recommendation method, device, system and storage medium | |
CA3204742A1 (en) | Systems and methods for service location optimization | |
CN116132613A (en) | Picture polling method of monitoring system, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO PAY ISSUE FEE |
|
AS | Assignment |
Owner name: KYNDRYL, INC., NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTERNATIONAL BUSINESS MACHINES CORPORATION;REEL/FRAME:058213/0912 Effective date: 20211118 |