CN103075999B - Real-time multi-target position detection method and system based on image - Google Patents
Real-time multi-target position detection method and system based on image Download PDFInfo
- Publication number
- CN103075999B CN103075999B CN201310025828.8A CN201310025828A CN103075999B CN 103075999 B CN103075999 B CN 103075999B CN 201310025828 A CN201310025828 A CN 201310025828A CN 103075999 B CN103075999 B CN 103075999B
- Authority
- CN
- China
- Prior art keywords
- real
- cloud terrace
- image
- time
- target
- 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.)
- Expired - Fee Related
Links
Abstract
The invention provides a real-time multi-target position detection method and a system based on an image and relates to a real-time visual detection technology. The invention solves the problem that a traditional real-time visual detection technology can not satisfy continuous real-time high-precision detection and adopts the main technical scheme that the method comprises the following steps: carrying out feedback control and adjustment on the position of a tripod head and calibrating real-time multi-target position detection system image pickup equipment based on the image. The real-time multi-target position detection method and the system have the outstanding advantages that the detection target direction of the image system can be quickly and accurately positioned; the calibration of the online real-time self-adaptive image system can be realized; and different detection demands can be satisfied, the image calibration precision is improved, and the measurement precision and the real time are improved.
Description
Technical field
The present invention relates to a kind of real-time vision detection technique, especially relate to a kind of real-time multi-target position detection method based on image and system.
Background technology
Along with the development of the progress of science and technology and computer vision technique, photogrammetric technology, make there has been the development of leap based on the picture control of video camera, the application of real-time vision detection technique in security protection industry, industrial environment in dimension of object and space position parameter etc.Real-time vision detection system has the advantages such as noncontact, dynamic range are large, abundant information, is subject to the attention of domestic and international fields of measurement.Real-time vision detects and can carry out static state independently, objectively to measured object or measure dynamically.Possibility can not be become to the measurement problem of measured object being installed sensing device for many.Real-time vision detection technique, as the one in noncontact measurement, is not only the function that simulation human eye completes, the more important thing is that it can complete the inefficient work of human eye.
Real-time vision detection technique adopts multi-vision visual to carry out three-dimensional measurement and utilizes principle of parallax, the multiple image of the same target detection scene obtained under different visual angles is processed, thus the three-dimensional coordinate information recovering target detection scene completes the detection of target detection scene location.And the acquisition of image coordinate is by the impact of vision facilities parameter (as internal optics, geometrical property, position relationship etc. between actual scene coordinate system and vision facilities).These parameters often affect by atmospheric temperature, wind direction, wind speed, sunshine and humidity etc., also have time variation simultaneously, make real-time vision detection system under execution multitask condition, are difficult to the needs meeting the detection of target detection scene location:
(1) based in the real-time vision detection system composition of video camera, The Cloud Terrace (can be divided into: have common The Cloud Terrace, spherical pan head, heavy monopod) at present, structure basic simlarity, there is horizontal drive motor inside, is used as the driving power of horizontal direction i.e. left and right directions; Motor vertical is used as above-below direction and drives.Drived control adopts open loop control mode, is difficult to meet the needs needing the multi-target detection scene location of matching sectional curve automatically to detect in real time.
(2) phase measurement adopts sinusoidal grating projection and phase-shifting technique, make the grating be projected on object, produce distortion, by the process to deforming stripe according to the height of object, demodulate the phase information of representative height, this method process is simple, and precision is higher, but can not eliminate the error that striped high-frequency noises causes, at graded larger part, grid line is intensive, and solution is mutually difficult, the needs that very difficult application needs the multi-target detection scene location of matching sectional curve to detect.
(3) due in real-time vision detection system, image capture apparatus is except completing the needs of position detection, also usually use as tasks such as picture controls, because the parameter of image capture apparatus is with the change inner parameter change or unstable of the different operation methods of operation, when detecting in position, there is the impact such as quantization error and nonlinear mirror scaphocephaly.
(4) measured by real-time vision, mostly be interior of building close shot, between image capture apparatus, base length is very little, thus causes the error of calculation larger.
Therefore, detect in application process at real-time vision, to vision facilities parameter and vision facilities reference coordinate automatic calibration, it is the important content realizing the detection of continuous real-time high-precision that target detection scene target is aimed at from motion tracking.
Summary of the invention
The invention provides a kind of real-time multi-target position detection method based on image and system, it carries out the difficult problem that when multiple goal position in sighting distance change procedure is detected, inner parameter scale is difficult and measuring accuracy is low under rotating for image capture apparatus in existing image measurement, with the locus self-correcting of self-calibration primary standard substance, tandem vision facilities is self-align is foundation, realizes the multiple goal location drawing as coordinate measurement.Under can be applicable to long line of sight conditions, the detection thing profile that bulk is large or long linear detection thing sectional curve recover the fields such as detection.
Goal of the invention of the present invention is achieved through the following technical solutions:
Based on a real-time multi-target position detection method for image, it is characterized in that, the method comprises the following steps:
(1) The Cloud Terrace zero-bit initialization, completes The Cloud Terrace level, vertical zero-bit self-correcting is demarcated;
(2) setting value of impact point was provided according to last sense cycle testing result;
(3) The Cloud Terrace is under the control of The Cloud Terrace position looped system, obtains target information of angle detection in image coordinate system;
(4) primary standard substance object images and inclination transducing signal corrected Calculation testing result is read;
(5) revised testing result and real-time physical parameter are compared, if parameter is identical, preserve the position coordinates of impact point, the position of then carrying out next impact point is detected; If parameter is different, then readjusts the setting value detecting impact point, forward step (3) to;
(6) judged whether that the position of all impact points is detected, if YES, then detection of end, otherwise forward step (2) to.
Preferably, the The Cloud Terrace zero-bit initialization described in step (1) completes under the control of The Cloud Terrace position looped system.
Preferably, the control of described The Cloud Terrace position looped system is specially, gathered level, the vertical deflection angle of The Cloud Terrace respectively by level, vertical two groups of photoelectricity orthogonal encoders, then export by controller level, the vertical drive servomotor that number percent conditioning signal drives The Cloud Terrace respectively.
Preferably, step (4) is specially, with a certain fixed character thing of detected system for primary standard substance, selected characteristic point on primary standard substance, unique point 2D picture point being connected is a quadrilateral or polygon, target plate is generated by sine streak gridding process, obtain the angle of inclination of target plate in conjunction with primary standard substance installation site, physical dimension and vision facilities fixed installation positional information and obtain demarcating target plate after the inclination transducing signal correction of primary standard substance, then utilizing and demarcate target plate corrected Calculation result.
Preferably, the real-time physical parameter described in step (5) is for being a quadrilateral or polygonal physical dimension with detected system a certain fixed character thing by selected characteristic point on primary standard substance connects.
Implement the claims a system for the method described in 1, it is characterized in that, this system comprises: The Cloud Terrace, for image capture; Deflection angle signal detector, for detecting level, the vertical deflection angle of The Cloud Terrace in real time; Microcontroller, for exporting according to the The Cloud Terrace level detected, vertical deflection angle level, the vertical drive servomotor that number percent conditioning signal drives The Cloud Terrace respectively; Primary standard substance inclination sensor, for the angle of inclination of detection reference thing; Image processor, for completing graphical analysis, process, draws the positional information of impact point.
Preferably, described The Cloud Terrace is common The Cloud Terrace, ball-shaped cloud platform or heavy monopod.
Preferably, described deflection angle signal detector is photoelectricity orthogonal encoder.
Preferably, the adjustment algorithm that described microcontroller adopts is proportional integral or apery PI.
Compared with prior art, the present invention has the following advantages:
1, in forming for the real-time vision detection system based on video camera, The Cloud Terrace drived control adopts open loop control mode, be difficult to meet need the multi-target detection scene location of matching sectional curve automatically to detect in real time needs and the not high difficult problem of measurement and positioning precision, employing level, vertical deflection angle signal realizes level by two groups of photoelectricity orthogonal codings respectively, vertical direction just, Reverse gantry detects and The Cloud Terrace Zero positioning, in conjunction with two separate proportional integrations (PI) or apery PI control strategy, export number percent conditioning signal respectively and drive level, vertical servo drives, realize picture system detection target direction quick, accurate location, needs are detected with the real-time follow-up realizing detected object multiple target point.
2. occur that non-uniform settling affects in conjunction with fixed reference thing in detected object system by the long term of the factor such as soil, meteorological condition, occur that primary standard substance tilts or change in displacement adopts the correction of outer inclination transducing signal based on the demarcation target plate of primary standard substance, realize the demarcation of online real-time adaptive picture system.
3. adopt the self-correcting cascade control system based on target image, regulate (control) inner ring to regulate composition with The Cloud Terrace track and localization, outer shroud self-correcting is demarcated target image and is regulated composition.Can ensure in object (point) testing process, the needs of the high precision test of effective field of view scope.Simultaneously in conjunction with detection system object actual conditions, the many demarcation target change detection based on many primary standard substances can be adopted in cycle detection, meet long-distance line detected object closely, the needs of middle distance, distant object thing (point).Be applicable to, in the real-time online vision detection system such as contours profiles detection as the line section curves such as transmission overhead line, large scale inspection thing, improve image calibration precision, improve measuring accuracy and real-time.
Accompanying drawing explanation
Fig. 1 is that the present invention is at current detection cycle (K) M impact point testing process flow diagram;
Fig. 2 is The Cloud Terrace position feedback control System's composition block diagram;
Fig. 3 is the self-correcting cascade control system block diagram based on target image.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
embodimenta kind of real-time multi-target position detection method based on image and system
Based on the real-time multi-target position detecting system of image, difficult and the low difficult problem of measuring accuracy of inner parameter scale when multiple goal position is detected is carried out in sighting distance change procedure under rotating for image capture apparatus in existing image measurement, with the locus self-correcting of self-calibration primary standard substance, tandem vision facilities is self-align is foundation, realizes the multiple goal location drawing as coordinate measurement.Under can be applicable to long line of sight conditions, the detection thing profile that bulk is large or long linear detection thing sectional curve recover the fields such as detection.It adds the improvement in following two on the basis of existing real-time detecting system:
1. add The Cloud Terrace position feedback control system
The Cloud Terrace position feedback control system embeds microcontroller in common The Cloud Terrace, and to being used as the driving kinetic servo motor of left and right directions in horizontal direction and being used as above-below direction in vertical direction and driving vertical servo electric machine rotation to carry out detections acquisition position signalling, this position signalling exports control command by position adjustments algorithm and acts on and drive servo control mechanism object compared with tracing detection goal-setting signal, realizes The Cloud Terrace position and automatically locates.To obtain real-time target angle (α, beta, gamma) Detection Information in image coordinate system.
As shown in Figure 2, the level of image capture apparatus The Cloud Terrace object, the detection of vertical deflection angle signal adopt photoelectricity orthogonal coding mode to detect to The Cloud Terrace position feedback control system works block scheme.Level, vertical deflection angle signal are respectively by two groups of photoelectricity orthogonal coding (A
0, B
0and A
1, B
1), realize level, vertical deflection signal detects and The Cloud Terrace zero-bit (0 degree, 0 degree) self-calibration.Level, vertical adjusting algorithm adopt two separate proportional integrations (PI) or apery PI control strategy respectively, export number percent conditioning signal signal respectively and drive level, vertical servo to drive.
2. based on the demarcation of the real-time multi-target position detecting system image capture apparatus of image
Known dimensions primary standard substance within the vision is adopted owing to being installed on ground reference target, long term by the factor such as soil, meteorological condition occurs that non-uniform settling affects, occur that primary standard substance tilts or displacement, by primary standard substance inclination transducing signal, self-correcting is carried out to reference target size, thus complete inside and outside parameter demarcation.In conjunction with real-time target angle (α, beta, gamma) Detection Information in image coordinate system, detect with realize target image coordinate.Reference target picture system based on primary standard substance is demarcated: the method with a certain fixed character thing of detected system for primary standard substance, selected characteristic point on primary standard substance.Unique point 2D picture point being connected is a quadrilateral or polygon, target plate is generated by sine streak gridding process, obtain the angle of inclination of target plate in conjunction with primary standard substance installation site, physical dimension and vision facilities fixed installation positional information and obtain demarcating target plate after the inclination transducing signal correction of primary standard substance, completing picture system in conjunction with optimized algorithms such as least square methods and demarcate.
Through dual image pickup apparatus image acquisition, obtain primary standard substance image by denoising, angle point grid, images match, cuts out, gridding, and deformity calculates generating reference target image.Two measurement data are completed inside and outside model parameter calculation by coordinate transform.Detected aims of systems thing (point) can adopt the image system coordinate information exporting object (point) shown in Fig. 3 based on the self-correcting cascade control system block diagram principle of target image.Detected system has object (point) P
0, P
1, P
2p
k, image capture apparatus with fixed base length from two different location C and C
/respectively with two angle shot objects (point) P
0, P
1, P
2p
k, complete characteristics of detection system point target coordinate build by setting up world's outdoor scene coordinate system and image coordinate system.Adopt the matching sectional curve based on neural network algorithm and least square method scheduling algorithm by unique point coordinate, obtain the needs that sensed system parameter detects.
As shown in Figure 1, in FIG, the initialization of The Cloud Terrace zero-bit can run once by actual detection system situation L sense cycle the inventive method, and the initialization of The Cloud Terrace zero-bit mainly completes The Cloud Terrace level, vertical zero-bit (0 degree, 0 degree) self-correcting is demarcated; Detect the setting of impact point i Place object by the adjustment of K-1 testing result to refer to and provide target set point in the last sense cycle testing result of current detection cycle K; Principle work shown in the figure of working envelope shown in Fig. 1 is pressed in the feedback regulation of The Cloud Terrace position, regulates algorithm to adopt conventional proportional integral or apery PI, exports number percent conditioning signal signal respectively and drives level, vertical servo to drive.It is a quadrilateral or polygonal physical dimension that real-time physical parameter to refer to a certain fixed character thing of detected system as selected characteristic point on primary standard substance is connected.The method comprises the following steps:
(1) The Cloud Terrace zero-bit initialization, completes The Cloud Terrace level, vertical zero-bit self-correcting is demarcated; Wherein, the initialization of The Cloud Terrace zero-bit completes under the control of The Cloud Terrace position looped system.The control of The Cloud Terrace position looped system is specially, gathered level, the vertical deflection angle of The Cloud Terrace respectively by level, vertical two groups of photoelectricity orthogonal encoders, then export by controller level, the vertical drive servomotor that number percent conditioning signal drives The Cloud Terrace respectively.
(2) setting value of impact point was provided according to last sense cycle testing result;
(3) The Cloud Terrace is under the control of The Cloud Terrace position looped system, obtains target information of angle detection in image coordinate system;
(4) primary standard substance object images and inclination transducing signal corrected Calculation testing result is read;
With a certain fixed character thing of detected system for primary standard substance, selected characteristic point on primary standard substance, unique point 2D picture point being connected is a quadrilateral or polygon, target plate is generated by sine streak gridding process, obtain the angle of inclination of target plate in conjunction with primary standard substance installation site, physical dimension and vision facilities fixed installation positional information and obtain demarcating target plate after the inclination transducing signal correction of primary standard substance, then utilizing and demarcate target plate corrected Calculation result.
(5) revised testing result and real-time physical parameter (real-time physical parameter for detected system a certain fixed character thing be a quadrilateral or polygonal physical dimension by selected characteristic point on primary standard substance is connected) are compared, if parameter is identical, preserve the position coordinates of impact point, the position of then carrying out next impact point is detected; If parameter is different, then readjusts the setting value detecting impact point, forward step (3) to;
(6) judged whether that the position of all impact points is detected, if YES, then detection of end, otherwise forward step (2) to.
In order to implement said method, designed system comprises: The Cloud Terrace, for image capture; Deflection angle signal detector, for detecting level, the vertical deflection angle of The Cloud Terrace in real time; Microcontroller, for exporting according to the The Cloud Terrace level detected, vertical deflection angle level, the vertical drive servomotor that number percent conditioning signal drives The Cloud Terrace respectively; Primary standard substance inclination sensor, for the angle of inclination of detection reference thing; Image processor, for completing graphical analysis, process, draws the positional information of impact point.
The Cloud Terrace is common The Cloud Terrace, ball-shaped cloud platform or heavy monopod.Deflection angle signal detector is photoelectricity orthogonal encoder.The adjustment algorithm that microcontroller adopts is proportional integral or apery PI.
The present invention is directed in the real-time vision detection system composition based on video camera, The Cloud Terrace drived control adopts open loop control mode, be difficult to meet need the multi-target detection scene location of matching sectional curve automatically to detect in real time needs and the not high difficult problem of measurement and positioning precision, employing level, vertical deflection angle signal realizes level by two groups of photoelectricity orthogonal codings respectively, vertical direction just, Reverse gantry detects and The Cloud Terrace Zero positioning, in conjunction with two separate proportional integrations (PI) or apery PI control strategy, export number percent conditioning signal respectively and drive level, vertical servo drives, realize picture system detection target direction quick, accurate location.Needs are detected with the real-time follow-up realizing detected object multiple target point.
By the long term of the factor such as soil, meteorological condition, the present invention occurs that non-uniform settling affects in conjunction with fixed reference thing in detected object system, occur that primary standard substance tilts or change in displacement adopts the correction of outer inclination transducing signal based on the demarcation target plate of primary standard substance, realize the demarcation of online real-time adaptive picture system.
The present invention adopts the self-correcting cascade control system based on target image, and regulate (control) inner ring to regulate composition with The Cloud Terrace track and localization, outer shroud self-correcting is demarcated target image and regulated composition.Can ensure in object (point) testing process, the needs of the high precision test of effective field of view scope.Simultaneously in conjunction with detection system object actual conditions, the many demarcation target change detection based on many primary standard substances can be adopted in cycle detection, meet long-distance line detected object closely, the needs of middle distance, distant object thing (point).Be applicable to, in the real-time online vision detection system such as contours profiles detection as the line section curves such as transmission overhead line, large scale inspection thing, improve image calibration precision, improve measuring accuracy and real-time.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, it should be pointed out that all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (11)
1. based on a real-time multi-target position detection method for image, it is characterized in that, the method comprises the following steps:
(1) be provided with the The Cloud Terrace zero-bit initialization of image capture apparatus, complete The Cloud Terrace level, vertical zero-bit self-correcting is demarcated;
(2) setting value of impact point was provided according to last sense cycle testing result;
(3) be provided with the The Cloud Terrace of image capture apparatus under the control of The Cloud Terrace position looped system, obtain target information of angle detection in image coordinate system;
(4) primary standard substance object images and inclination transducing signal corrected Calculation testing result is read;
(5) revised testing result and real-time physical parameter are compared, if parameter is identical, preserve the position coordinates of impact point, the position of then carrying out next impact point is detected; If parameter is different, then readjusts the setting value detecting impact point, forward step (3) to;
(6) judged whether that the position of all impact points is detected, if YES, then detection of end, otherwise forward step (2) to.
2. a kind of real-time multi-target position detection method based on image according to claim 1, is characterized in that, the The Cloud Terrace zero-bit initialization described in step (1) completes under the control of The Cloud Terrace position looped system.
3. a kind of real-time multi-target position detection method based on image according to claim 1 and 2, it is characterized in that, the control of described The Cloud Terrace position looped system is specially, gathered level, the vertical deflection angle of The Cloud Terrace respectively by level, vertical two groups of photoelectricity orthogonal encoders, then export by controller level, the vertical drive servomotor that number percent conditioning signal drives The Cloud Terrace respectively.
4. a kind of real-time multi-target position detection method based on image according to claim 1, it is characterized in that, step (4) is specially, with a certain fixed character thing of detected system for primary standard substance, selected characteristic point on primary standard substance, unique point 2D picture point being connected is a polygon, target plate is generated by sine streak gridding process, in conjunction with primary standard substance installation site, physical dimension and vision facilities fixed installation positional information obtain the angle of inclination of target plate and obtain demarcating target plate after the inclination transducing signal correction of primary standard substance, then utilize and demarcate target plate corrected Calculation result.
5. a kind of real-time multi-target position detection method based on image according to claim 4, is characterized in that, described polygon is quadrilateral.
6. a kind of real-time multi-target position detection method based on image according to claim 1, it is characterized in that, the real-time physical parameter described in step (5) is for being a polygonal physical dimension with a certain fixed character thing of detected system by selected characteristic point on primary standard substance connects.
7. a kind of real-time multi-target position detection method based on image according to claim 6, is characterized in that, described polygon is quadrilateral.
8. implement the claims a system for the method described in 1, it is characterized in that, this system comprises:
Be provided with the The Cloud Terrace of image capture apparatus, for image capture;
Deflection angle signal detector, for detecting level, the vertical deflection angle of The Cloud Terrace in real time;
Microcontroller, for exporting according to the The Cloud Terrace level detected, vertical deflection angle level, the vertical drive servomotor that number percent conditioning signal drives The Cloud Terrace respectively;
Primary standard substance inclination sensor, for the angle of inclination of detection reference thing;
Image processor, for completing graphical analysis, process, draws the positional information of impact point.
9. system according to claim 8, is characterized in that, described The Cloud Terrace is common The Cloud Terrace, ball-shaped cloud platform or heavy monopod.
10. system according to claim 8, is characterized in that, described deflection angle signal detector is photoelectricity orthogonal encoder.
11. systems according to claim 8, is characterized in that, the adjustment algorithm that described microcontroller adopts is proportional integral.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310025828.8A CN103075999B (en) | 2013-01-23 | 2013-01-23 | Real-time multi-target position detection method and system based on image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310025828.8A CN103075999B (en) | 2013-01-23 | 2013-01-23 | Real-time multi-target position detection method and system based on image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103075999A CN103075999A (en) | 2013-05-01 |
| CN103075999B true CN103075999B (en) | 2014-12-24 |
Family
ID=48152613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310025828.8A Expired - Fee Related CN103075999B (en) | 2013-01-23 | 2013-01-23 | Real-time multi-target position detection method and system based on image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103075999B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106611147B (en) * | 2015-10-15 | 2018-10-16 | 腾讯科技（深圳）有限公司 | Car tracing method and apparatus |
| CN107976445B (en) * | 2016-10-21 | 2022-08-19 | 上海交通大学 | Plane position measuring method and system |
| CN109543496B (en) * | 2017-09-22 | 2020-11-27 | 杭州海康威视数字技术股份有限公司 | Image acquisition method and device, electronic equipment and system |
| CN109000303A (en) * | 2018-07-25 | 2018-12-14 | 浙江工业大学 | Tracking heating device and the method certainly of carrying space temperature field recognition |
| CN110321396A (en) * | 2019-05-27 | 2019-10-11 | 深圳市迈测科技股份有限公司 | Position calibration method and Related product |
| CN110827288B (en) * | 2019-10-08 | 2022-08-12 | 歌尔光学科技有限公司 | Method and device for extracting target image in projector definition test |
| CN112995505B (en) * | 2021-02-09 | 2022-06-17 | 西南科技大学 | Image processing method, device and storage medium |
| CN115842848B (en) * | 2023-03-01 | 2023-04-28 | 成都远峰科技发展有限公司 | Dynamic monitoring system based on industrial Internet of things and control method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5512733A (en) * | 1989-12-14 | 1996-04-30 | Mitsubishi Denki Kabushiki Kaisha | Cooker |
| CN102143324A (en) * | 2011-04-07 | 2011-08-03 | 天津市亚安科技电子有限公司 | Method for automatically and smoothly tracking target by cradle head |
| CN102314182A (en) * | 2011-06-24 | 2012-01-11 | 天津市亚安科技电子有限公司 | Cradle head locating method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100081049A (en) * | 2009-01-05 | 2010-07-14 | 삼성전자주식회사 | Apparatus and method for photographing image in portable terminal |
-
2013
- 2013-01-23 CN CN201310025828.8A patent/CN103075999B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5512733A (en) * | 1989-12-14 | 1996-04-30 | Mitsubishi Denki Kabushiki Kaisha | Cooker |
| CN102143324A (en) * | 2011-04-07 | 2011-08-03 | 天津市亚安科技电子有限公司 | Method for automatically and smoothly tracking target by cradle head |
| CN102314182A (en) * | 2011-06-24 | 2012-01-11 | 天津市亚安科技电子有限公司 | Cradle head locating method and device |
Non-Patent Citations (2)
| Title |
|---|
| 一种新型的智能云台控制系统;李昌坤等;《中国测试技术》;20050531;第31卷(第3期);第30-32页 * |
| 输电线路实时参数运行检测研究;张阳等;《四川理工学院学报( 自然科学版)》;20120630;第25卷(第3期);第64-66页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103075999A (en) | 2013-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103075999B (en) | Real-time multi-target position detection method and system based on image | |
| EP3011362B1 (en) | Systems and methods for tracking location of movable target object | |
| CN103900489B (en) | A kind of line laser scanning three-dimensional contour measuring method and device | |
| CN103557796B (en) | 3 D positioning system and localization method based on laser ranging and computer vision | |
| EP2807472B1 (en) | Automated system and method for tracking and detecting discrepancies on a target object | |
| CN103941748A (en) | Autonomous navigation method and system and map modeling method and system | |
| CN106092059B (en) | A kind of works Horizontal Displacement Monitoring Method based on multi-point fitting | |
| CN206193235U (en) | Electric power inspection is two -dimensional laser radar calibration device for robot | |
| CN103090845B (en) | Remote distance measurement method based on plurality of images | |
| CN106556826B (en) | Intelligent Mobile Robot location navigation two-dimensional laser Radar Calibration device and method | |
| CN104075688A (en) | Distance measurement method of binocular stereoscopic gazing monitoring system | |
| CN109737883A (en) | A kind of three-dimensional deformation dynamic measurement system and measurement method based on image recognition | |
| CN105043259A (en) | Numerical control machine tool rotating shaft error detection method based on binocular vision | |
| US11820001B2 (en) | Autonomous working system, method and computer readable recording medium | |
| US20220390233A1 (en) | Movable marking system, controlling method for movable marking apparatus, and computer readable recording medium | |
| CN106197292A (en) | A kind of building displacement monitoring method | |
| CN106651957B (en) | Monocular vision object space localization method based on template | |
| CN104050669A (en) | On-line calibration method based on vanishing point and monocular camera image-forming principle | |
| Pásztó et al. | Mobile robot navigation based on circle recognition | |
| CN106125066B (en) | The control system and control method of laser radar | |
| CN113289290A (en) | Fire-fighting robot flame automatic aiming method, device and system | |
| CN115790387A (en) | Bridge displacement corner synchronous real-time monitoring method and system based on online camera | |
| CN110702343B (en) | Deflection measurement system and method based on stereoscopic vision | |
| CN103175512A (en) | Shooting measurement method of attitude of tail end of boom of concrete pump truck | |
| CN110207605A (en) | A kind of measuring device and method of the metal structure deformation based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141224 Termination date: 20170123 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |