CN101883261A - 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
- CN101883261A CN101883261A CN 201010191162 CN201010191162A CN101883261A CN 101883261 A CN101883261 A CN 101883261A CN 201010191162 CN201010191162 CN 201010191162 CN 201010191162 A CN201010191162 A CN 201010191162A CN 101883261 A CN101883261 A CN 101883261A
- Authority
- CN
- China
- Prior art keywords
- target
- tracking
- image
- mrow
- module
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 23
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 20
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000007246 mechanism Effects 0.000 claims 1
- 230000010354 integration Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 241001290762 Pratia Species 0.000 description 1
- 230000036626 alertness Effects 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 150000003839 salts Chemical class 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 invention relates to pattern recognition, in particular to a method and a system for abnormal target detection and relay tracking in a large-range monitoring scene.
Background
With the rapid development of computer technology and digital electronic technology, visual monitoring technology is more and more widely applied. The traditional visual monitoring system can only provide video acquisition and storage functions, monitoring personnel need to watch the display screen in a monitoring room to find abnormal conditions, monitoring cost is increased, visual fatigue caused by watching the display screen for a long time can reduce the alertness of the monitoring personnel, and the monitoring system can not play a due role at certain key moments. Currently, intelligent visual monitoring technology is emerging and is receiving increasing attention from media. The intelligent visual monitoring technology is to make a computer replace the brain of a person, make a camera replace the eyes of the person, and make the computer intelligently analyze an image sequence obtained from the camera to understand the content in a monitored scene. The abnormal target detection and relay tracking technology under the large-range monitoring scene is an intelligent visual monitoring technology with application value, target information in important monitoring scenes with wide areas, such as a park, a square and the like, can be acquired in real time through a large number of fixed cameras, targets with abnormal behaviors are alarmed, a pan-tilt camera is controlled to carry out relay tracking on the targets, and a powerful tool is provided for safety defense of important areas.
One of the main difficulties of the abnormal target detection and relay tracking technology in the large-range monitoring scene is how to comprehensively analyze the target information detected by a plurality of cameras in the large-range scene. The target detection technology of a single fixed camera generally adopts a gaussian background modeling method to establish a background of a fixed scene, then obtains a foreground image by subtracting the obtained image from the background image, and finally analyzes and processes the foreground image to obtain target information in the image (Chris Stauffer, W.E.L. Grimson. adaptive background mix models for real-time tracking.1999 IEEE Computer Society Conference on video and Pattern recognition.IEEE Computer ut. Soc. part Vol.2, 1999). However, the field of view monitored by a single camera is limited, and the monitoring of a large-range scene cannot be realized; if a plurality of cameras are used for monitoring, the following problems can occur: 1) the same abnormal behavior appears in the public view field of the two cameras, so that two times of alarms for the same abnormal behavior appear; 2) the same target sequentially appears in the images a and b of the two cameras, and the target possibly has abnormal behavior in the camera a and does not have abnormal behavior in the camera b, so that the condition that the camera a gives an alarm, and the target moves to the monitoring area of the camera b and is shown as a normal target appears; 3) for most abnormal behavior analysis methods based on target motion trajectories, abnormal behaviors of edge regions of images cannot be detected. Therefore, the abnormal target detection technology of a single camera cannot be simply expanded for solving the abnormal target detection of multiple cameras in a large-range monitoring scene.
Another major difficulty of the abnormal target detection and relay Tracking technology in the large-scale monitoring scene is how to realize relay Tracking of the same target by Multiple pan-tilt cameras (Calderara S, PratiA, Vezzani R, Persistent Objects Tracking Across Multiple Non overlapping cameras, wacv/MOTION' 05, vol.2). Almost all relay tracking methods relate to target matching, characteristics such as color, texture, point line and the like of a target need to be extracted, requirements on image quality and application scenes are high, and the method is not suitable for outdoor large-scale target relay tracking.
Disclosure of Invention
The invention aims to provide a method and a system for detecting an abnormal target and tracking relay in a large-range monitoring scene.
According to one aspect of the invention, a method for detecting and relay tracking abnormal targets in a large-range monitoring scene comprises the following steps:
video input and frame extraction;
sub-sampling the image;
modeling a Gaussian background;
calculating the position of the target block in the digital map;
tracking and recording a track of a target;
detecting target abnormal behaviors;
and detecting and relay tracking the target.
According to another aspect of the present invention, a system for abnormal target detection and relay tracking in a large-scale monitoring scenario includes:
the target detection module is used for carrying out Gaussian background modeling by utilizing the sub-sampled image to obtain a foreground image, calculating the coordinates of the target in the digital map and then sending the coordinate information to the target identification and tracking control module;
the target identification and tracking control module is used for completing target tracking, track recording and target abnormal behavior detection, if abnormal behavior occurs, selecting a proper pan-tilt camera according to the target coordinate information, and sending an alarm signal 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 camera to perform preset position steering according to the content of the alarm information, and then detecting and tracking the moving target.
The invention solves the problem of fusion of multi-path image target information in a large-range monitoring scene. Accurate and robust relay tracking of the same target is achieved. The calculation amount is moderate, and the requirement of real-time video processing can be met.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a foreground object motion trajectory in a digital map at a time;
FIG. 3 is an image of an anomalous target taken by the high-altitude camera;
FIG. 4 is a pan-tilt camera tracking target;
FIG. 5 is a system composition diagram;
FIG. 6 is a system information flow diagram;
fig. 7 is a functional diagram of a module.
Detailed Description
The flow chart of the whole technical scheme of the invention is shown in the attached figure 1. The technical details involved in the invention are explained below, and finally an example of an application in a certain campus is given.
1. Video input and frame decimation
The digital image sequence transmitted from the camera is generally 25 frames/second, and because multiple paths of images need to be acquired and processed simultaneously in a large-range monitoring scene, the frame rate needs to be properly reduced, and the calculation amount needs to be reduced. Generally, a frame-by-frame processing mode can be adopted, and the processing speed is reduced to 13 frames/second, so that a better detection effect is ensured.
2. Sub-sampling of images
For the same reason as step 1, it is necessary to reduce the resolution of the image to increase the processing speed. The image is sub-sampled by adopting a Gaussian pyramid decomposition method, so that the loss of image quality caused by sub-sampling is reduced to a certain extent.
Wherein,
representing a gaussian convolution kernel, σ is the standard deviation of the gaussian distribution, typically taken to be 0.85. I (x, y) and I (x, y) represent the values of the pixels of the sub-sampled image and the original image at (x, y), respectively. L denotes the size of the gaussian convolution kernel and r denotes the sub-sampling rate. Generally, r is 2, and L is 3, so that a sub-sampled image can be obtained under the condition of ensuring the image quality.
3. Gaussian background modeling
Image foreground was detected by the method of Gaussian background modeling (P.KadewTrKuPong, R.Bowden, "improved adaptive background mix model for real-time tracking with shadow detection" in Proc.2nd European workshop on Advanced Video-based Surveillance Systems, 2001.). The foreground image obtained by the method has relatively large noise, and the salt and pepper noise in the foreground image is eliminated by adopting a median filtering mode; then, connecting the split target blocks in the foreground image by using an expansion method to obtain a binary image with the foreground target blocks; finally, obtaining the pixel position information of all target blocks in the binary image and recording the pixel position information as a set Si＝{(xi，yi) And indicating the foreground object information of the ith video. The size of the median filter is selected to be 3 x 3 or 5 x 5 for image quality, and the size of the dilation operator is selected to be 3 x 3.
4. Calculating the position of a target block in a digital map
Collecting S image pixel coordinates of video foreground target blockiMapping the set S 'onto a digital map by a perspective transformation matrix to obtain a set S'i＝{(x′j，y′j) 1, … n, and represents a coordinate set of a target block in the current image of the ith video on the digital map, and S 'is { S'1∪S′2…∪S′x| x ═ video path number }. The digital map and the actual scene are completely corresponding, and a perspective transformation matrix M between the coordinates of the digital map and the coordinates of the video imageiObtained by the formula 1. From equation 1, knowing the coordinates of the corresponding points in the four pairs of digital map and video images, the perspective transformation matrix M between them can be solvedi。
(t·x′，t·y′，t)T＝Mi·(x，y，1)T (1)
Wherein, (x, y) represents the image coordinates of the foreground target block, (x ', y') represents the coordinates of the foreground target block on the digital map, T is an arbitrary constant, i represents the number of the multi-channel video, M represents a perspective transformation matrix, and T is a matrix-to-rank symbol.
5. Target tracking and trajectory recording
Using the set O { (x)jk，yjk) And | j ∈ (1, … N), k ∈ (1, … m) } represents the track set of all historical foreground objects, wherein j represents the index of different objects, and k represents different time instants. (x)jk，yjk) Indicating the position of target k at time j. For a set of currently derived foreground target block coordinates, S { (x'i，y′i) I 1, … n, using nearest neighbor to track the target and adding its record in the set O.
Specifically, let O' { (x)jm，yjm) And | j ∈ (1, … N) }, which represents the set of m-time track points of all historical foreground objects. For each element (x ') in set S'i，y′i) Calculating the element (x) in the set O' nearest to the elementtm，ytm) And distance is recorded as LtIf there is LtIf T is established, m is m +1, and a new trace point is added to the set O, (x)tm，ytm) (ii) a Otherwise, (x'i，y′i) The set O is added as a new target's trace point. Where T is typically 20 and the unit is a pixel. Fig. 2 shows the movement locus of a foreground object in a part of a digital map at a certain moment, fig. 3 shows an abnormal object image shot by a corresponding high-altitude camera, and the abnormal object in the image is marked by a red frame.
6. Detection of target anomalous behavior
The definition of the abnormal target is different depending on the application context, and generally, monitoring of a wide-range scene is concerned about whether or not an object mainly made of a person has abnormal behaviors such as crossing a border, wandering a specific area, and the like. The abnormal target related to the monitoring method refers to the fact that the target crosses the warning line and the target loiters in the warning area. And judging whether the target has the abnormal behavior or not by analyzing the track of the target. If the current track point of the target is on the outer side of the warning line and the initial track point is on the inner side of the warning line, the target is considered to be out of range; and if the target track point exceeds the set time t in the warning area, the target warning area is considered to be loitering.
7. Tracking and relay tracking of targets
When an abnormal target alarm occurs, the pan-tilt camera closest to the abnormal target performs preset position steering according to the position of the target on a map, so that the target appears in the view field of the pan-tilt camera (the preset position of the pan-tilt needs to be preset); then reading in the video collected by the pan-tilt-zoom camera, calculating a binary differential image of adjacent image frames, and calculating the gravity center (x) of the binary differential image when the number of nonzero pixels of the binary differential image is greater than a constant W (W is determined according to the size and the view field of the image and is generally 2000)0，y0) As the center of the anomaly target; finally, the color histogram feature of the target is extracted, and the target is tracked by using the Camshift method (Computer Vision Face Tracking For Use in a Perceptial User Interface, Intel Technology Journal, No. Q2.1998).
When an abnormal target appears, the pan-tilt camera a tracks, when the target moves to another position and is closer to the pan-tilt camera b, the pan-tilt camera b carries out preset position steering and detects and tracks the moving target, and therefore relay tracking is achieved. Fig. 4 is an image of a pan-tilt camera tracking a target.
The above is a detailed description of the implementation steps of the present invention, and the following takes an example of an abnormal target detection and relay tracking system in an office park of a certain institution, and gives experimental results.
The system comprises a target detection module, a target identification and tracking control module and an active tracking module. The target detection module consists of eight fixed high-altitude cameras arranged at the top of the building and two target detection hosts; the target identification and tracking control module consists of a target identification and tracking control host; the active tracking module consists of eight pan-tilt cameras installed on the ground and eight active tracking hosts. The system composition diagram is shown in fig. 5.
The system has the following working flow that a plurality of (eight in the example, more or fewer high-altitude cameras can be arranged as required) high-altitude cameras are used for carrying out full-coverage monitoring on the whole park, video signals of the high-altitude cameras are accessed into at least one target detection host (two in the example, more or less than two can be used as required), real-time intelligent analysis is carried out, targets in images are detected, target information is formed, and the target information is sent to a target identification and tracking control host through a local area network; the target recognition and tracking control host comprehensively processes target information sent by the two target detection hosts, forms and analyzes the position and the motion track of a target, forms alarm information (including a cradle head camera which should be selected for tracking the target and preset position steering which should be carried out by the cradle head camera) for the target which accords with the abnormal behavior alarm triggering rule, and sends the alarm information to a proper active tracking host through a local area network; and a plurality of active tracking hosts (eight are used in the embodiment, more than eight or less than eight can be used as required) control corresponding pan-tilt cameras to perform preset position steering according to the content of the alarm information, so that the target triggering the alarm appears in the field of view of the camera, and starts to perform moving target detection, positioning and active tracking. Fig. 6 is a system information flow diagram.
The system has three modules: the system comprises a target detection module, a target identification and tracking control module and an active tracking module. The functional diagram of each module is shown in FIG. 7. The target detection module has the main functions of utilizing the sub-sampled image to carry out Gaussian background modeling to obtain a foreground image and calculating the position of a target block in a digital map; the target identification and tracking control module mainly completes target tracking and track recording and detection of target abnormal behaviors; the active tracking module is mainly used for receiving the alarm information of the target identification and tracking control module, controlling the pan-tilt camera to perform preset position steering according to the content of the alarm information, displaying the target triggering alarm in the view field of the pan-tilt camera, performing motion analysis on the image, extracting the characteristic information of the target, and then controlling the pan-tilt to rotate according to the characteristics to perform target tracking.
Claims (19)
1. A method for detecting and tracking abnormal targets in a large-range monitoring scene comprises the following steps:
video input and frame extraction;
sub-sampling the image;
modeling a Gaussian background;
calculating the position of the target block in the digital map;
tracking and recording a track of a target;
detecting target abnormal behaviors;
and detecting and relay tracking the target.
2. The method of claim 1, wherein the video is captured using a video camera.
3. The method of claim 1, wherein the decimating is performed by a frame-by-frame process.
4. The method of claim 1, wherein the image is sub-sampled by a gaussian pyramid decomposition.
5. The method of claim 4, wherein the image is sub-sampled using the following formula:
wherein I (x, y) and I (x, y) represent values of pixels of the sub-sampled image and the original image at (x, y), respectively, L represents a size of a Gaussian convolution kernel, r represents a sub-sampling rate,
representing a gaussian convolution kernel and σ is the standard deviation of the gaussian distribution.
6. The method of claim 5, wherein σ is 0.85, r is 2, and L is 3.
7. The method according to claim 1, wherein the foreground of the image is obtained by a gaussian background modeling method, and the median filtering and expansion operations are performed on the foreground image to finally obtain the pixel position information of all target blocks in the binary image.
8. The method of claim 1, wherein the image coordinates of the object are mapped to digital map coordinates by a perspective transformation matrix M.
9. The method of claim 8, wherein the perspective transformation matrix M between the digital map coordinates and the image coordinates is obtained by the following formula:
(t·x′，t·y′，t)T＝M·(x，y，1)T
wherein, (x, y) represents the image coordinates of the foreground target block, (x ', y') represents the coordinates of the foreground target block on the digital map, T is an arbitrary constant, M represents a perspective transformation matrix, and T is a matrix conversion rank symbol.
10. The method of claim 1, wherein for the set of digital map coordinates of all foreground objects, tracking is performed using nearest neighbor and the trajectory is recorded.
11. The method of claim 1, wherein the target abnormal behavior comprises one of:
the current track point of the target is arranged outside the warning line, and the initial track point is arranged inside the warning line;
the target track point exceeds the set time in the warning area.
12. The method of claim 1, wherein the target tracking comprises:
and detecting a moving target by calculating a binary differential image of adjacent image frames, and tracking the target by a Camshift method.
13. The method of claim 1, wherein the target relay tracking comprises:
and through the position of the target on the digital map, the pan-tilt camera performs preset position steering, so that the target appears in the view field of the pan-tilt camera.
14. A system for abnormal target detection and relay tracking under a large-range monitoring scene comprises:
the target detection module is used for carrying out Gaussian background modeling by utilizing the sub-sampled image to obtain a foreground image, calculating the coordinates of the target in the digital map and then sending the coordinate information to the target identification and tracking control module;
the target identification and tracking control module is used for completing target tracking, track recording and target abnormal behavior detection, if abnormal behavior occurs, selecting a proper pan-tilt camera according to the target coordinate information, and sending an alarm signal 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 camera to perform preset position steering according to the content of the alarm information, and then detecting and tracking the moving target.
15. The system of claim 14, wherein the object detection module comprises a plurality of cameras and at least two object detection mechanisms.
16. The system of claim 14, wherein the target recognition and tracking control module is comprised of a target recognition and tracking control host.
17. The system of claim 145, wherein the active tracking module comprises a plurality of pan-tilt cameras and a plurality of active tracking hosts.
18. The system of claim 15, wherein the plurality of cameras are positioned at high altitudes.
19. The system of claim 17, wherein the pan-tilt camera is positioned 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 true CN101883261A (en) | 2010-11-10 |
| CN101883261B 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) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156983A (en) * | 2011-03-31 | 2011-08-17 | 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 |
| CN102568003A (en) * | 2011-12-21 | 2012-07-11 | 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 |
| CN102982537A (en) * | 2012-11-05 | 2013-03-20 | 安维思电子科技（广州）有限公司 | Scene change detection method and scene change detection system |
| CN103077533A (en) * | 2012-12-26 | 2013-05-01 | 中国科学技术大学 | Method for positioning moving target based on frogeye visual characteristics |
| CN103310442A (en) * | 2013-05-16 | 2013-09-18 | 南京航空航天大学 | Multi-frequency information fusion-based intelligent positioning system and method |
| CN103795984A (en) * | 2014-02-07 | 2014-05-14 | 彭世藩 | Self-learning omnibearing mobile monitoring system |
| CN103841374A (en) * | 2012-11-27 | 2014-06-04 | 华为技术有限公司 | Display method and system for video monitoring image |
| CN104077779A (en) * | 2014-07-04 | 2014-10-01 | 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 |
| CN104504401A (en) * | 2015-01-09 | 2015-04-08 | 成都新舟锐视科技有限公司 | Target identification system based on multiple 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 |
| WO2015101047A1 (en) * | 2014-01-03 | 2015-07-09 | 杭州海康威视系统技术有限公司 | Method and device for extracting surveillance record videos |
| CN104931038A (en) * | 2014-03-19 | 2015-09-23 | 中广核工程有限公司 | System and method for positioning and navigating staff in nuclear power station |
| CN105279485A (en) * | 2015-10-12 | 2016-01-27 | 江苏精湛光电仪器股份有限公司 | Detection method for monitoring abnormal behavior of target under laser night vision |
| CN105844634A (en) * | 2016-03-18 | 2016-08-10 | 阜阳师范学院 | Multi-motion-object video monitoring system and tracking monitoring method thereof |
| CN106373160A (en) * | 2016-08-31 | 2017-02-01 | 清华大学 | Active camera target positioning method based on depth reinforcement learning |
| WO2017084262A1 (en) * | 2015-11-19 | 2017-05-26 | 杭州海康威视数字技术股份有限公司 | Method for monitoring moving target, and monitoring device, apparatus and system |
| CN107004271A (en) * | 2016-08-22 | 2017-08-01 | 深圳前海达闼云端智能科技有限公司 | Display methods, device, electronic equipment, computer program product and non-transient computer readable storage medium storing program for executing |
| 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 |
| 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 |
| CN108924482A (en) * | 2018-06-22 | 2018-11-30 | 张小勇 | A kind of video recording method and system |
| CN110113560A (en) * | 2018-02-01 | 2019-08-09 | 中兴飞流信息科技有限公司 | The method and server of video intelligent linkage |
| 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 |
| CN110781796A (en) * | 2019-10-22 | 2020-02-11 | 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 |
| CN110956644A (en) * | 2018-09-27 | 2020-04-03 | 杭州海康威视数字技术股份有限公司 | Motion trail determination method and system |
| CN111034189A (en) * | 2017-08-30 | 2020-04-17 | 三菱电机株式会社 | Imaging object tracking device and imaging object tracking method |
| CN111460917A (en) * | 2020-03-13 | 2020-07-28 | 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 |
| CN111477013A (en) * | 2020-04-01 | 2020-07-31 | 清华大学苏州汽车研究院（吴江） | Vehicle measuring method based on map image |
| CN112468765A (en) * | 2019-09-06 | 2021-03-09 | 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 |
| TWI757756B (en) * | 2019-11-28 | 2022-03-11 | 大陸商深圳市商湯科技有限公司 | Pedestrian event detection method and detection device, electronic device and computer-readable storage medium |
| CN114827466A (en) * | 2022-04-20 | 2022-07-29 | 武汉三江中电科技有限责任公司 | Human eye-imitated equipment image acquisition device and image acquisition method |
| CN116958884A (en) * | 2023-09-18 | 2023-10-27 | 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 |
| CN101470809A (en) * | 2007-12-26 | 2009-07-01 | 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 |
| CN101470809A (en) * | 2007-12-26 | 2009-07-01 | 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 |
|---|
| 《工程图学学报》 20011231 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 第28-33页 , 2 * |
| 《计算机学报》 20030430 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 第417-426页 1-19 第26卷, 第4期 2 * |
Cited By (58)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156983A (en) * | 2011-03-31 | 2011-08-17 | 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 |
| CN102568003A (en) * | 2011-12-21 | 2012-07-11 | 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 |
| CN102982537A (en) * | 2012-11-05 | 2013-03-20 | 安维思电子科技（广州）有限公司 | Scene change detection method and scene change detection 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 |
| CN103841374A (en) * | 2012-11-27 | 2014-06-04 | 华为技术有限公司 | Display method and system for video monitoring image |
| CN103841374B (en) * | 2012-11-27 | 2017-04-12 | 华为技术有限公司 | Display method and system for video monitoring image |
| WO2014082407A1 (en) * | 2012-11-27 | 2014-06-05 | 华为技术有限公司 | Method and system for displaying 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 |
| CN103077533A (en) * | 2012-12-26 | 2013-05-01 | 中国科学技术大学 | Method for positioning moving target based on frogeye visual characteristics |
| CN103310442A (en) * | 2013-05-16 | 2013-09-18 | 南京航空航天大学 | Multi-frequency information fusion-based intelligent positioning system and 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 |
| WO2015101047A1 (en) * | 2014-01-03 | 2015-07-09 | 杭州海康威视系统技术有限公司 | Method and device for extracting surveillance record videos |
| US9736423B2 (en) | 2014-01-03 | 2017-08-15 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and apparatus for extracting surveillance recording videos |
| CN103795984A (en) * | 2014-02-07 | 2014-05-14 | 彭世藩 | Self-learning omnibearing mobile monitoring system |
| CN104931038A (en) * | 2014-03-19 | 2015-09-23 | 中广核工程有限公司 | System and method for positioning and navigating staff in nuclear power station |
| CN104077779A (en) * | 2014-07-04 | 2014-10-01 | 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 |
| 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 |
| CN104504401A (en) * | 2015-01-09 | 2015-04-08 | 成都新舟锐视科技有限公司 | Target identification system based on multiple monitoring probes |
| 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 |
| CN105279485A (en) * | 2015-10-12 | 2016-01-27 | 江苏精湛光电仪器股份有限公司 | Detection method for monitoring abnormal behavior of target under laser night vision |
| 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 |
| WO2017084262A1 (en) * | 2015-11-19 | 2017-05-26 | 杭州海康威视数字技术股份有限公司 | Method for monitoring moving target, and monitoring device, apparatus and system |
| CN105844634A (en) * | 2016-03-18 | 2016-08-10 | 阜阳师范学院 | Multi-motion-object video monitoring system and tracking monitoring method thereof |
| 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 |
| CN107004271A (en) * | 2016-08-22 | 2017-08-01 | 深圳前海达闼云端智能科技有限公司 | Display methods, device, electronic equipment, computer program product and non-transient computer readable storage medium storing program for executing |
| CN106373160A (en) * | 2016-08-31 | 2017-02-01 | 清华大学 | Active camera target positioning method based on depth reinforcement learning |
| 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 |
| CN111034189A (en) * | 2017-08-30 | 2020-04-17 | 三菱电机株式会社 | Imaging object tracking device 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 |
| CN110113560A (en) * | 2018-02-01 | 2019-08-09 | 中兴飞流信息科技有限公司 | The method and server of video intelligent linkage |
| 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 |
| CN108924482A (en) * | 2018-06-22 | 2018-11-30 | 张小勇 | A kind of 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 |
| CN110956644A (en) * | 2018-09-27 | 2020-04-03 | 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 |
| CN112468765A (en) * | 2019-09-06 | 2021-03-09 | 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 |
| CN110781796A (en) * | 2019-10-22 | 2020-02-11 | 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 |
| TWI757756B (en) * | 2019-11-28 | 2022-03-11 | 大陸商深圳市商湯科技有限公司 | Pedestrian event detection method and detection device, electronic device and computer-readable storage medium |
| CN111460917A (en) * | 2020-03-13 | 2020-07-28 | 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 |
| 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 |
| CN111477013A (en) * | 2020-04-01 | 2020-07-31 | 清华大学苏州汽车研究院（吴江） | Vehicle measuring method based on map image |
| CN114827466A (en) * | 2022-04-20 | 2022-07-29 | 武汉三江中电科技有限责任公司 | Human eye-imitated equipment image acquisition device and image acquisition method |
| CN116958884A (en) * | 2023-09-18 | 2023-10-27 | 杭州靖安防务科技有限公司 | Method and system for target tracking |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101883261B (en) | 2012-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101883261B (en) | Method and system for abnormal target detection and relay tracking under large-range monitoring scene | |
| US10339386B2 (en) | Unusual event detection in wide-angle video (based on moving object trajectories) | |
| CN103024350B (en) | A kind of principal and subordinate's tracking of binocular PTZ vision system and the system of application the method | |
| CN101277429B (en) | Method and system for amalgamation process and display of multipath video information when monitoring | |
| AU2012340862B2 (en) | Geographic map based control | |
| CN109872483B (en) | Intrusion alert photoelectric monitoring system and method | |
| CN112084963B (en) | Monitoring early warning method, system and storage medium | |
| US11037308B2 (en) | Intelligent method for viewing surveillance videos with improved efficiency | |
| CN101141633A (en) | Moving object detecting and tracing method in complex scene | |
| CN104378582A (en) | Intelligent video analysis system and method based on PTZ video camera cruising | |
| CN111161312B (en) | Object trajectory tracking and identifying device and system based on computer vision | |
| Kumar et al. | Multiple cameras using real time object tracking for surveillance and security system | |
| Divya et al. | Inspection of suspicious human activity in the crowdsourced areas captured in surveillance cameras | |
| CN105930814A (en) | Method for detecting personnel abnormal gathering behavior on the basis of video monitoring platform | |
| CN100496122C (en) | Method for tracking principal and subordinate videos by using single video camera | |
| CN114092851A (en) | Monitoring video abnormal event detection method based on time sequence action detection | |
| Aitfares et al. | Suspicious behavior detection of people by monitoring camera | |
| CN203279057U (en) | Multi-target intelligent tracking locking and monitoring system | |
| CN113194249A (en) | Moving object real-time tracking system and method based on camera | |
| Yamashita et al. | Removal of adherent noises from image sequences by spatio-temporal image processing | |
| CN113361364A (en) | Target behavior detection method, device, equipment and storage medium | |
| US11044399B2 (en) | Video surveillance system | |
| Aramvith et al. | Video processing and analysis for surveillance applications | |
| Tong et al. | Human positioning based on probabilistic occupancy map | |
| US20230102949A1 (en) | Enhanced three dimensional visualization using artificial intelligence |
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: 20121212 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |