CN101883261B - Method and system for abnormal target detection and relay tracking under large-range monitoring scene - Google Patents
Method and system for abnormal target detection and relay tracking under large-range monitoring scene Download PDFInfo
- Publication number
- CN101883261B CN101883261B CN 201010191162 CN201010191162A CN101883261B CN 101883261 B CN101883261 B CN 101883261B CN 201010191162 CN201010191162 CN 201010191162 CN 201010191162 A CN201010191162 A CN 201010191162A CN 101883261 B CN101883261 B CN 101883261B
- Authority
- CN
- China
- Prior art keywords
- target
- tracking
- image
- module
- coordinate
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 title abstract 2
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 21
- 238000005070 sampling Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 claims 1
- 230000010354 integration Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 1
- 241001290762 Pratia Species 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a method and a system for abnormal target detection and relay tracking under a large-range monitoring scene. The system comprises a target detection module, a target identification and tracking control module and an active tracking module, wherein the target detection module is used for carrying out Gaussian background modeling by utilizing a sub-sampled image to obtain a foreground image, computing the coordinate of a target in a digital map and then sending coordinate information to the target identification and tracking control module; the target identification and tracking control module is used for finishing the target tracking, the track recording and the abnormal behavior detection of the target, and if abnormal behavior occurs, a proper pan-tilt video camera is selected according to the coordinate information of the target, and an alarm signal is sent to the active tracking module; and the active tracking module is used for receiving the alarm information of the target identification and tracking control module, controlling the pan-tilt video camera to carry out preset position steering according to the content of the alarm information and then carrying out the detection and the tracking of the moving target. The invention solves the integration problem of multiple paths of image target information under the large-range monitoring scene and realizes the accurate and robust relay tracking of the same target.
Description
Technical field
The present invention relates to pattern recognition, particularly the unusual target detection under the large-range monitoring scene and the method and system of relay tracking.
Background technology
Along with computer technology and digital electric technology rapid development, vision monitoring technology have obtained application more and more widely.Traditional visual monitor system often can only provide the function of video acquisition and storage; Need the monitor staff to watch display screen to come unusual circumstance at Control Room; Not only increased monitoring cost; And the visual fatigue of watching display screen to cause for a long time can make monitor staff's vigilance reduce, and makes supervisory control system can not bring into play due effect at some crucial moment.At present, the intelligent vision monitoring technology is risen, and more and more receives the concern of medium.The intelligent vision monitoring technology will let computer generation replace people's brain exactly; Let camera replace people's eyes; Analyze the image sequence that from camera, obtains by computer intelligence ground, the content in the monitored scene is understood, compared remarkable advantages with traditional visual monitor system; The quantity that can significantly reduce the monitor staff reduces cost, and makes things convenient for resource (security personnel, police strength etc.) scheduling.Unusual target detection under the large-range monitoring scene and relay tracking technology are a kind of intelligent vision monitoring technology that has very much using value; Through a large amount of fixed cameras; It can obtain the target information in the more wide important monitoring scene in garden, square homalographic in real time; Target with abnormal behaviour is reported to the police and controlled monopod video camera it is carried out relay tracking, for the safety guard of important area provides strong instrument.
A main difficult point of unusual target detection and relay tracking technology is a plurality of video cameras of analysis-by-synthesis detected separately target information under scene on a large scale how under the large-range monitoring scene.The target detection technique of single fixed cameras generally adopts the method for Gaussian Background modeling to set up the background of fixed scene; The mode of subtracting each other through the image that obtains and background image then obtains foreground image; At last target information (the Chris Stauffer that obtains in the image is analyzed, handled to foreground image; W.E.L Grimson.Adaptive background mixture models for real-time tracking.1999 IEEE Computer Society Conference on Computer Vision and PatternRecognition.IEEE Comput.Soc.Part Vol.2,1999).But the visual field of single camera monitoring is limited, can't realize the monitoring of scene on a large scale; If adopt a plurality of camera supervisedly, have following problem: 1) appear at the public view field of two video cameras, thereby twice warning occur to same abnormal behaviour with an abnormal behaviour; 2) same target appears among two camera review a, the b successively; Possible this target has abnormal behaviour in a video camera; And in the b video camera, not having abnormal behaviour; Report to the police thereby a video camera occurs, and target travel shows as the situation of normal target to the camera supervised zone of b; 3) for the abnormal behaviour analytical method of most based target movement locus, the abnormal behaviour in edge of image zone can't detect.So, for the unusual target detection of multiple-camera that solves under the large-range monitoring scene, unusual target detection technique that can not the simple extension single camera.
Another main difficult point of unusual target detection and relay tracking technology is how to realize relay tracking (the Calderara S of a plurality of monopod video cameras to same target under the large-range monitoring scene; PratiA; Vezzani R; Persistent Objects Tracking Across Multiple Non OverlappingCameras.WACV/MOTION ' 05, Vol.2).Because nearly all relay tracking method relates to the coupling of target, characteristics such as the color of needs extraction target, texture, dotted line are had relatively high expectations to picture quality and application scenarios, are not suitable for outdoor large-scale target relay tracking.
Summary of the invention
The purpose of this invention is to provide unusual target detection and the method and system of relay tracking under a kind of large-range monitoring scene.
According to one side of the present invention, the unusual target detection under a kind of large-range monitoring scene and the method for relay tracking comprise step:
Video input and frame extract;
Image is carried out sub-sampling;
The Gaussian Background modeling;
Calculate the position of object block in numerical map;
Target is followed the tracks of and track record;
Target abnormal behaviour is detected;
Target is detected and relay tracking.
According to another aspect of the present invention, the unusual target detection under a kind of large-range monitoring scene and the system of relay tracking comprise:
Module of target detection utilizes the image of sub-sampling to carry out the Gaussian Background modeling, obtains foreground image, and calculates the coordinate of target in numerical map, sends to the target recognition and tracking control module to coordinate information then;
The target recognition and tracking control module is accomplished the detection of target following and track record and target abnormal behaviour, if abnormal behaviour takes place, according to the suitable monopod video camera of this coordinates of targets Information Selection, sends alarm signal to the active tracking module;
The active tracking module, the warning message of receiving target recognition and tracking control module carries out presetting bit according to warning message content control monopod video camera and turns to, and carries out motion target detection and tracking then.
The invention solves under the large-range monitoring scene fusion of multiway images target information.Realized same target accurately, the relay tracking of robust.Amount of calculation is moderate, can satisfy the real-time video treatment requirement.
Description of drawings
Fig. 1 is a technical scheme flow chart of the present invention;
Fig. 2 is the foreground target movement locus in certain moment numerical map;
Fig. 3 is the unusual target image that the high-altitude video camera is taken;
Fig. 4 is the monopod video camera tracking target;
Fig. 5 is system's composition diagram;
Fig. 6 is the system information flow graph;
Fig. 7 is functions of modules figure.
Embodiment
Whole technical proposal flow chart of the present invention is shown in accompanying drawing 1.Explain in the face of involved ins and outs in the invention down, provide an application example in certain machine-operated garden at last.
1. video input and frame extract
The digital image sequence that transmits from camera was generally for 25 frame/seconds, and owing under the large-range monitoring scene, need multiway images be gathered simultaneously, handle, so need suitable reduction frame per second, reduced amount of calculation.Generally can adopt the mode of handling at a distance from frame, be reduced to the processing speed of 13 frame/seconds, guarantee quite good detecting effectiveness like this.
2. the sub-sampling of image
Because same with step 1, the resolution that needs to reduce image is to improve processing speed.The method that has adopted gaussian pyramid to decompose is carried out sub-sampling to image, has reduced the loss of image quality that sub-sampling brings to a certain extent.
Wherein,
expression Gaussian convolution nuclear; σ is the standard variance of Gaussian distribution, gets 0.85 usually.I (x, y) and i (x, the pixel of y) representing image and original image behind the sub-sampling respectively is in (x, the value of y) locating.L representes the size of Gaussian convolution nuclear, and r representes the sub-sampling rate.General r gets 2, and L gets 3, can under the situation that guarantees picture quality, obtain the image of sub-sampling.
3. Gaussian Background modeling
Method (P.KadewTraKuPong through the Gaussian Background modeling; R.Bowden; " Animproved adaptive background mixture model for real-time tracking withshadow detection " in Proc.2nd European Workshp on Advanced Video-BasedSurveillance Systems, 2001.) the detected image prospect.The foreground image that obtains through this method has bigger noise, adopts the mode of medium filtering to eliminate the salt-pepper noise in the foreground image here; With the method that expands the object block that divides in the foreground image is connected then, obtain the bianry image that a width of cloth has the foreground target piece; Obtain the location of pixels information of all object block in this bianry image at last, note is made S set
i={ (x
i, y
i), represent the foreground target information of i road video.The big or small view picture element amount of median filter chooses 3 * 3 or 5 * 5, and expansion operator size chooses 3 * 3.
4. calculate the position of object block in numerical map
The image pixel coordinate set S of video foreground object block
i, be mapped on the numbered map through perspective transformation matrix, obtain S set '
i=(x '
j, y '
j) | j=1 ... N} representes the coordinate set of object block on numerical map in the present image of i road video, note S '=S '
1∪ S '
2∪ S '
x| x=video way }.Numerical map is corresponding fully with actual scene, the perspective transformation matrix M between numerical map coordinate and the video image coordinate
iThrough type 1 obtains.According to formula 1, the coordinate of the corresponding points in known four pairs of numerical maps and the video image just can solve the perspective transformation matrix M between them
i
(t·x′，t·y′，t)
T＝M
i·(x，y，1)
T (1)
Wherein, (x, the y) image coordinate of expression foreground target piece, (x ', y ') coordinate of expression foreground target piece on numerical map, t is an arbitrary constant, and i representes the numbering of multi-channel video, and M representes perspective transformation matrix, and T is that matrix changes the order symbol.
5. target following and track record
With set O={ (x
Jk, y
Jk) | j ∈ (1 ... N), k ∈ (1 ... M) } track of representing all historical foreground targets is gathered, and wherein j representes the index of different target, and k representes the different moment.(x
Jk, y
Jk) expression j target k position constantly.For the S set of the current foreground target piece coordinate that obtains '=(x '
i, y '
i) | i=1 ... N} adopts nearest neighbor algorithm to realize the tracking of target, and in set O, increases its record.
Specifically, note O '={ (x
Jm, y
Jm) | j ∈ (1 ... N) }, represent the m set of tracing point constantly of all historical foreground targets.For S set ' in each element (x '
i, y '
i), the element (x nearest among the set of computations O ' with it
Tm, y
Tm), distance is designated as L
tIf L is arranged
t＜T sets up, and increases a new tracing point, (x among then m=m+1, and the set O
Tm, y
Tm); Otherwise, (x '
i, y '
i) add set O as the tracing point of fresh target.Wherein, T generally gets 20, and unit is a pixel.Fig. 2 has represented the foreground target movement locus in certain part numerical map constantly, and Fig. 3 is the unusual target image that corresponding high-altitude video camera is taken, and the unusual target among the figure is annotated with red collimation mark.
6. the detection of target abnormal behaviour
The definition of unusual target is in response to different and difference is arranged with background more, generally speaking, and the abnormal behaviour whether care of the monitoring of scene on a large scale has that crossing the border, paces up and down in the specific region etc. with artificial master's target.The unusual target that this monitoring method relates to refers to that target is crossed warning line and target is paced up and down in warning region.Through the trajectory analysis of target is judged whether target has described abnormal behaviour.If the current tracing point of target in the warning line outside and start track point in the warning line inboard, think that this target crosses the border; If target trajectory point surpasses setting-up time t in warning region, think that this target security area paces up and down.
7. the tracking of target and relay tracking
When unusual target taking place report to the police, the nearest monopod video camera of the unusual target of distance carries out presetting bit and turns to according to the position of target on map, makes target appear among the visual field of monopod video camera (needing to set in advance the presetting bit of The Cloud Terrace); Read in the video that monopod video camera is gathered then, calculate the two-value difference image of adjacent image frame, as two-value difference image non-zero pixels number during (W decide according to image size, visual field, is generally 2000), the center of gravity (x of calculating two-value difference image greater than constant W
0, y
0), as the center of unusual target; Extract the color histogram characteristic of target at last; Adopt the CamShift method that target is followed the tracks of (Computer Vision Face Tracking For Use in aPerceptual User Interface; Intel Technology Journal, No.Q2.1998).
If when unusual target occurred, a monopod video camera was followed the tracks of, when this target travel to another position, more near the b monopod video camera, then the b monopod video camera carries out presetting bit and turns to, and carries out motion target detection and tracking, thereby realizes relay tracking.Fig. 4 is the image of monopod video camera tracking target.
More than being exactly the detailed description of implementation step of the present invention, is example with certain office's office unusual target detection in garden and relay tracking system below, provides experimental result.
This system comprises module of target detection, target recognition and tracking control module, active tracking module.Module of target detection is made up of eight fixedly high-altitude video camera and two target detection main frames that are installed in the top, building; The target recognition and tracking control module is made up of a target recognition and tracking main control system; Initiatively tracking module is initiatively followed the tracks of main frame by eight surface-based monopod video cameras and eight and is constituted.System's composition diagram is as 5.
The system works flow process is following, by many (this example is eight, can be many as required if establish the high-altitude video camera less) high-altitude video cameras whole garden is carried out all standing monitoring; The high-altitude camera video signal inserts at least one target detection main frame, and (this example is two; Can use as required greater or less than two), carry out the real-time intelligent analysis, the target in the detected image; Form target information, and send to the target recognition and tracking main control system through local area network (LAN); The target information that two target detection main frames of target recognition and tracking main control system integrated treatment send over; Form the also position and the movement locus of evaluating objects; To meeting the target of abnormal behaviour warning triggering rule; Form warning message (comprising that following the tracks of the presetting bit that monopod video camera that this target should select and this monopod video camera should carry out turns to), and send to the suitable main frame of initiatively following the tracks of through local area network (LAN); Initiatively follow the tracks of main frame (eight of this example uses for many; Can use more than eight as required or be less than eight) carry out presetting bit according to the corresponding monopod video camera of warning message content control and turn to; The target that triggers warning is appeared within this camera field of view, begin to carry out moving object detection, location and initiatively tracking.Fig. 6 is the system information flow graph.
Native system is totally three modules: module of target detection, target recognition and tracking control module, active tracking module.Each functions of modules figure such as Fig. 7.The major function of module of target detection is to utilize the image of sub-sampling to carry out the Gaussian Background modeling, obtains foreground image, and calculates the position of object block in numerical map; The target recognition and tracking control module is mainly accomplished the detection of target following and track record and target abnormal behaviour; Initiatively tracking module is mainly accomplished the warning message of receiving target recognition and tracking control module; Carrying out presetting bit according to warning message content control monopod video camera turns to; The target that triggers warning is presented in the visual field of monopod video camera; And image carried out motion analysis, and extract clarification of objective information, rotate according to these characteristics control The Cloud Terraces then and carry out target following.
Claims (15)
1. the unusual target detection under the large-range monitoring scene and the method for relay tracking comprise step:
Adopt multiple cameras seizure video and extract frame of video;
Image is carried out sub-sampling, wherein, adopts following formula sub-sampling image:
Wherein, and I (x, y) and i (x; Y) pixel of representing image and original image behind the sub-sampling respectively is in that (L representes the size of Gaussian convolution nuclear for x, the value of y) locating; L gets 3; R representes the sub-sampling rate, and r gets 2,
expression Gaussian convolution nuclear; σ is the standard variance of Gaussian distribution, and σ gets 0.85;
The Gaussian Background modeling;
Calculate the position of object block in numerical map;
Target is followed the tracks of and track record;
Target abnormal behaviour is detected;
Target is detected and relay tracking.
2. according to right 1 said method, it is characterized in that adopting at a distance from the frame processing video is done extraction.
3. according to right 1 said method; It is characterized in that obtaining the prospect of image through the Gaussian Background modeling method; And foreground image carried out medium filtering and expansive working, obtain the location of pixels information of all object block in the bianry image of medium filtering and expansive working.
4. according to right 1 said method, it is characterized in that being mapped as the numerical map coordinate to the image coordinate of target through perspective transformation matrix M.
5. according to right 4 said methods, it is characterized in that the perspective transformation matrix M between numerical map coordinate and the image coordinate obtains through following formula:
(t·x′，t·y′，t)
T＝M·(x，y，1)
T
Wherein, (x, the y) image coordinate of expression foreground target piece, (x ', y ') coordinate of expression foreground target piece on numerical map, t is an arbitrary constant, and M representes perspective transformation matrix, and T is that matrix changes the order symbol.
6. according to right 1 said method, it is characterized in that set, use nearest neighbor algorithm to follow the tracks of for the numerical map coordinate of all foreground targets, and recording track.
7. according to right 1 said method, it is one of following to it is characterized in that said target abnormal behaviour comprises:
The current tracing point of target in the warning line outside and start track point in the warning line inboard;
Target trajectory point surpasses setting-up time in warning region.
8. according to right 1 said method, it is characterized in that said target following comprises:
Two-value difference image through calculating the adjacent image frame detects moving target, through the CamShift method target is followed the tracks of.
9. according to right 1 said method, it is characterized in that said target relay tracking comprises:
Through the position of target on numerical map, monopod video camera carries out presetting bit and turns to, and makes target appear in the visual field of said monopod video camera.
10. the unusual target detection under the large-range monitoring scene and the system of relay tracking comprise:
Module of target detection utilizes the image of sub-sampling to carry out the Gaussian Background modeling, obtains foreground image; And the coordinate of calculating target in numerical map; Send to the target recognition and tracking control module to coordinate information then, wherein, adopt following formula sub-sampling image:
Wherein, and I (x, y) and i (x; Y) pixel of representing image and original image behind the sub-sampling respectively is in that (L representes the size of Gaussian convolution nuclear for x, the value of y) locating; L gets 3; R representes the sub-sampling rate, and r gets 2,
expression Gaussian convolution nuclear; σ is the standard variance of Gaussian distribution, and σ gets 0.85;
The target recognition and tracking control module is accomplished the detection of target following and track record and target abnormal behaviour, if abnormal behaviour takes place, according to the suitable monopod video camera of this coordinates of targets Information Selection, sends alarm signal to the active tracking module;
The active tracking module, the warning message of receiving target recognition and tracking control module carries out presetting bit according to warning message content control monopod video camera and turns to, and carries out motion target detection and tracking then.
11., it is characterized in that said module of target detection is made up of multiple cameras and two target detection mechanisms at least according to right 10 said systems.
12., it is characterized in that said target recognition and tracking control module is made up of the target recognition and tracking main control system according to right 10 said systems.
13., it is characterized in that said active tracking module initiatively follows the tracks of main frame by many monopod video cameras and Duo Tai and constitute according to right 10 said systems.
14. system according to claim 11 is characterized in that said multiple cameras is arranged on the high-altitude.
15. system according to claim 13 is characterized in that said monopod video camera setting on the ground.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010191162 CN101883261B (en) | 2010-05-26 | 2010-05-26 | Method and system for abnormal target detection and relay tracking under large-range monitoring scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010191162 CN101883261B (en) | 2010-05-26 | 2010-05-26 | Method and system for abnormal target detection and relay tracking under large-range monitoring scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101883261A CN101883261A (en) | 2010-11-10 |
| CN101883261B true CN101883261B (en) | 2012-12-12 |
Family
ID=43055135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010191162 Expired - Fee Related CN101883261B (en) | 2010-05-26 | 2010-05-26 | Method and system for abnormal target detection and relay tracking under large-range monitoring scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101883261B (en) |
Families Citing this family (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156983B (en) * | 2011-03-31 | 2013-03-20 | 上海交通大学 | Pattern recognition and target tracking based method for detecting abnormal pedestrian positions |
| CN102497507A (en) * | 2011-12-12 | 2012-06-13 | 山西奥克斯电子系统工程中心 | Image-analysis-based pan/tilt/zoom (PTZ) camera preset position control method |
| CN102568003B (en) * | 2011-12-21 | 2015-04-08 | 北京航空航天大学深圳研究院 | Multi-camera target tracking method based on video structural description |
| CN102854897A (en) * | 2012-09-28 | 2013-01-02 | 上海元朔信息科技有限公司 | Abnormal target finding and tracking system and method |
| CN102917207A (en) * | 2012-10-24 | 2013-02-06 | 沈阳航空航天大学 | Motion sequence based abnormal motion vision monitoring system |
| CN102982537B (en) * | 2012-11-05 | 2015-09-02 | 安维思电子科技（广州）有限公司 | A kind of method and system detecting scene change |
| CN103841374B (en) * | 2012-11-27 | 2017-04-12 | 华为技术有限公司 | Display method and system for video monitoring image |
| CN103077533B (en) * | 2012-12-26 | 2016-03-02 | 中国科学技术大学 | A kind of based on frogeye visual characteristic setting movement order calibration method |
| CN103310442B (en) * | 2013-05-16 | 2016-04-13 | 南京航空航天大学 | Based on intelligent positioning system and the localization method thereof of multifrequency information fusion |
| CN104717462A (en) | 2014-01-03 | 2015-06-17 | 杭州海康威视系统技术有限公司 | Supervision video extraction method and device |
| CN103795984A (en) * | 2014-02-07 | 2014-05-14 | 彭世藩 | Self-learning omnibearing mobile monitoring system |
| CN104931038B (en) * | 2014-03-19 | 2018-05-01 | 中广核工程有限公司 | Nuclear power station staff positions and the system and method for navigation |
| CN104077779B (en) * | 2014-07-04 | 2017-01-25 | 中国航天科技集团公司第五研究院第五一三研究所 | Moving object statistical method with Gaussian background model and mean value shift tracking combined |
| CN104463900A (en) * | 2014-12-31 | 2015-03-25 | 天津汉光祥云信息科技有限公司 | Method for automatically tracking target among multiple cameras |
| CN104504401B (en) * | 2015-01-09 | 2018-08-31 | 成都新舟锐视科技有限公司 | A kind of target identification system based on more monitoring probes |
| CN104639916A (en) * | 2015-03-04 | 2015-05-20 | 合肥巨清信息科技有限公司 | Large-scene multi-target tracking shooting video monitoring system and monitoring method thereof |
| CN104680557A (en) * | 2015-03-10 | 2015-06-03 | 重庆邮电大学 | Intelligent detection method for abnormal behavior in video sequence image |
| CN104702917A (en) * | 2015-03-25 | 2015-06-10 | 成都市灵奇空间软件有限公司 | Video concentrating method based on micro map |
| CN105279485B (en) * | 2015-10-12 | 2018-12-07 | 江苏精湛光电仪器股份有限公司 | The detection method of monitoring objective abnormal behaviour under laser night vision |
| CN106791586A (en) * | 2015-11-19 | 2017-05-31 | 杭州海康威视数字技术股份有限公司 | A kind of method and monitoring device, device, system being monitored to mobile target |
| CN105844634B (en) * | 2016-03-18 | 2019-04-05 | 阜阳师范学院 | A kind of multiple mobile object tracking monitor method |
| WO2018035667A1 (en) * | 2016-08-22 | 2018-03-01 | 深圳前海达闼云端智能科技有限公司 | Display method and apparatus, electronic device, computer program product, and non-transient computer readable storage medium |
| CN106373160B (en) * | 2016-08-31 | 2019-01-11 | 清华大学 | A kind of video camera active target localization method based on deeply study |
| US11004211B2 (en) * | 2017-08-30 | 2021-05-11 | Mitsubishi Electric Corporation | Imaging object tracking system and imaging object tracking method |
| CN107909598A (en) * | 2017-10-28 | 2018-04-13 | 天津大学 | A kind of moving object detection and tracking method based on interprocess communication |
| CN110113560B (en) * | 2018-02-01 | 2021-06-04 | 中兴飞流信息科技有限公司 | Intelligent video linkage method and server |
| CN108711247A (en) * | 2018-06-08 | 2018-10-26 | 陕西艾利克斯光电科技有限公司 | A kind of circumference defence denial system dispersing function with non-lethal acousto-optic |
| CN108924482B (en) * | 2018-06-22 | 2021-03-23 | 张小勇 | Video recording method and system |
| CN110956644B (en) * | 2018-09-27 | 2023-10-10 | 杭州海康威视数字技术股份有限公司 | Motion trail determination method and system |
| CN110222675A (en) * | 2019-07-02 | 2019-09-10 | 同略科技有限公司 | A kind of police strength dispatching method, system, terminal and storage medium |
| CN112468765B (en) * | 2019-09-06 | 2022-04-15 | 杭州海康威视系统技术有限公司 | Method, device, system, equipment and storage medium for tracking target object |
| CN110781796B (en) * | 2019-10-22 | 2022-03-25 | 杭州宇泛智能科技有限公司 | Labeling method and device and electronic equipment |
| CN110830767A (en) * | 2019-10-31 | 2020-02-21 | 深圳大学 | Active intelligent behavior analysis alarm device |
| CN110969115B (en) * | 2019-11-28 | 2023-04-07 | 深圳市商汤科技有限公司 | Pedestrian event detection method and device, electronic equipment and storage medium |
| CN111460917B (en) * | 2020-03-13 | 2022-06-21 | 温州大学大数据与信息技术研究院 | Airport abnormal behavior detection system and method based on multi-mode information fusion |
| CN111477013B (en) * | 2020-04-01 | 2021-06-25 | 清华大学苏州汽车研究院（吴江） | Vehicle measuring method based on map image |
| CN114827466B (en) * | 2022-04-20 | 2023-07-04 | 武汉三江中电科技有限责任公司 | Human eye-like equipment image acquisition device and image acquisition method |
| CN116958884B (en) * | 2023-09-18 | 2024-01-16 | 杭州靖安防务科技有限公司 | Method and system for target tracking |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101098465A (en) * | 2007-07-20 | 2008-01-02 | 哈尔滨工程大学 | Moving object detecting and tracing method in video monitor |
| CN101266710A (en) * | 2007-03-14 | 2008-09-17 | 中国科学院自动化研究所 | An all-weather intelligent video analysis monitoring method based on a rule |
| CN101299275A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method and device for detecting target as well as monitoring system |
| CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
| CN101470809B (en) * | 2007-12-26 | 2011-07-20 | 中国科学院自动化研究所 | Moving object detection method based on expansion mixed gauss model |
-
2010
- 2010-05-26 CN CN 201010191162 patent/CN101883261B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101266710A (en) * | 2007-03-14 | 2008-09-17 | 中国科学院自动化研究所 | An all-weather intelligent video analysis monitoring method based on a rule |
| CN101098465A (en) * | 2007-07-20 | 2008-01-02 | 哈尔滨工程大学 | Moving object detecting and tracing method in video monitor |
| CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
| CN101470809B (en) * | 2007-12-26 | 2011-07-20 | 中国科学院自动化研究所 | Moving object detection method based on expansion mixed gauss model |
| CN101299275A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method and device for detecting target as well as monitoring system |
Non-Patent Citations (2)
| Title |
|---|
| 昌娅，胡卫明，谭铁牛.交通视觉监控系统中的三维车辆线框模型可视化算法.《工程图学学报》.2001,第28-33页. * |
| 胡卫明,谢丹,谭铁牛,沈俊.轨迹分布模式学习的层次自组织神经网络方法.《计算机学报》.2003,第26卷(第4期),第417-426页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101883261A (en) | 2010-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101883261B (en) | Method and system for abnormal target detection and relay tracking under large-range monitoring scene | |
| CN105447458B (en) | A kind of large-scale crowd video analytic system and method | |
| CN107145851A (en) | Constructions work area dangerous matter sources intelligent identifying system | |
| CN104378582A (en) | Intelligent video analysis system and method based on PTZ video camera cruising | |
| EP1854083B1 (en) | Object tracking camera | |
| CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
| CN111967393A (en) | Helmet wearing detection method based on improved YOLOv4 | |
| CN104123544A (en) | Video analysis based abnormal behavior detection method and system | |
| CN102447835A (en) | Non-blind-area multi-target cooperative tracking method and system | |
| CN104038729A (en) | Cascade-type multi-camera relay tracing method and system | |
| CN111242025B (en) | Real-time action monitoring method based on YOLO | |
| EP2783508A1 (en) | Geographic map based control | |
| CN103413321A (en) | Crowd behavior model analysis and abnormal behavior detection method under geographical environment | |
| CN102184551A (en) | Automatic target tracking method and system by combining multi-characteristic matching and particle filtering | |
| CN110458897A (en) | Multi-cam automatic calibration method and system, monitoring method and system | |
| CN111143504B (en) | Multi-camera indoor video map construction method | |
| CN112449093A (en) | Three-dimensional panoramic video fusion monitoring platform | |
| CN107610393A (en) | A kind of intelligent office monitoring system | |
| CN105427345A (en) | Three-dimensional people stream movement analysis method based on camera projection matrix | |
| CN102426785A (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
| Choeychuen | Available car parking space detection from webcam by using adaptive mixing features | |
| CN105095891A (en) | Human face capturing method, device and system | |
| Ellis | Multi-camera video surveillance | |
| CN109977796A (en) | Trail current detection method and device | |
| CN103700106A (en) | Distributed-camera-based multi-view moving object counting and positioning method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121212 |