CN103150736A - Camera motion detecting method based on video monitoring - Google Patents
Camera motion detecting method based on video monitoring Download PDFInfo
- Publication number
- CN103150736A CN103150736A CN2012104883404A CN201210488340A CN103150736A CN 103150736 A CN103150736 A CN 103150736A CN 2012104883404 A CN2012104883404 A CN 2012104883404A CN 201210488340 A CN201210488340 A CN 201210488340A CN 103150736 A CN103150736 A CN 103150736A
- Authority
- CN
- China
- Prior art keywords
- background
- video camera
- point
- frame
- video
- 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.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a camera motion detecting method based on video monitoring. The method comprises the steps of collecting video frames, conducting background building through the Gaussian mixture model, sampling random points around every pixel point through a random sampling method, initializing the background, differentiating the obtained present frame with a background frame, conducting statistics of the number of the pixel points smaller than 20, regarding the point as a background point when the number of the pixel points is bigger than 2, regarding the point as a foreground point when the number of the pixel points is not bigger than 2, and judging whether the camera is moved through a comparison with a certain fixed threshold value according to the number of the pixel points of a foreground frame. Camera motion detecting is achieved.
Description
Technical field
The present invention relates to technical field of computer vision, particularly a kind of video camera movement detection method based on video monitoring.
Background technology
Along with the development of science and technology and the people continuous enhancing to security precautions, video monitoring system of new generation with intellectual analysis function, the various aspects that have been widely used in society are as traffic, military affairs, airport, bank, video conference, business, industry etc.
Intelligent video monitoring refers in the situation that do not need human intervention, utilize the computer vision analysis method to carry out automatic analysis to video sequence, realize moving object detection, classification, identification, tracking etc., and on this basis, by predefined rule, the behavior of target is analyzed, thereby provided for taking further measures with reference to (such as enter when district automatic alarm of setting up defences at object).Yet will have a strong impact on the performance of intelligent video monitoring system when the disturbed appearance of video camera is abnormal.In the large-scale intelligent supervisory system, because the number of video camera is numerous, be difficult to be found when video camera is disturbed, this just needs supervisory system to have self-detectability, can in time note abnormalities to remind the staff to process rapidly, increases work efficiency.
At present, it is generally acknowledged that the video camera interference refers to that violent variation appears in monitored picture, and the lasting regular hour, some of short duration accidental variations are considered as normally.Its type mainly contains: video camera is blocked, video camera is moved, video camera is out of focus, video camera is acutely shaken, video camera imaging brightness is abnormal, video camera imaging distortion, fault of camera etc.Wherein, video camera moves to detect and refers to that monitored picture switches to suddenly other scene, and may cause very large impact this moment to intelligent video monitoring system.At present, video camera Interference Detection algorithm mainly contains two kinds of background subtraction and neighbor frame difference methods, the background modeling of background subtraction and renewal are more difficult, operand is larger, the real-time effect is general, and the neighbor frame difference method utilizes the variation of adjacent two frames or a few frame differences to judge whether interference occurs, and is generally fairly simple, can detect rapidly interference, shortcoming is that rate of false alarm is higher.
Move accuracy of detection in order to improve video camera, existing video camera movement detection method based on video monitoring provides a kind of video camera movement detection method based on video monitoring, at first the method gathers frame of video, utilize mixed Gauss model to carry out background constructing, recycling stochastic sampling method is sampled to the random point around each pixel, and the initialization background; Then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.The method has very high accuracy and robustness, has effectively solved the video camera under the complex background and has moved the problem of detection, reaches purpose of design.
Summary of the invention
The invention provides a kind of video camera movement detection method based on video monitoring; the method can realize that the video camera under complex scene moves detection; solved in the scene of complexity; usually can there be the interference (as illumination variation, dynamic background element etc.) of various extraneous factors, has a strong impact on the problem of accuracy of detection.
To achieve these goals, the present invention includes following technical characterictic: comprise at first gathering frame of video, utilize mixed Gauss model to carry out background constructing, recycling stochastic sampling method is sampled to the random point around each pixel, and the initialization background; Then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.
Compare with existing method, the present invention proposes and at first obtain frame of video, utilize the mixed Gauss model method, and adopt the method initialization background of stochastic sampling; Then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.The method has very high accuracy and robustness, has effectively solved in complicated scene, and the interference of the various extraneous factors of existence (as illumination variation, dynamic background element etc.) causes the problem of wrong report.
Description of drawings
Accompanying drawing is overview flow chart of the present invention.
Embodiment
The present invention has designed a kind of video camera movement detection method based on video monitoring, the method can realize that the video camera under complex scene moves detection, have very high accuracy and robustness, effectively solved in complicated scene, the interference of the various extraneous factors of existence (as illumination variation, dynamic background element etc.) causes the problem of wrong report.
As shown in drawings, the method process flow diagram comprises the collection frame of video, utilizes mixed Gauss model to carry out background modeling; And utilize stochastic sampling method initialization background, and then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.
Specific implementation is: comprise the collection frame of video; Utilize mixed Gauss model to carry out background modeling, and adopt the method initialization background of stochastic sampling; Then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.
Described from obtaining frame of video, utilize mixed Gaussian to carry out background modeling, and adopt stochastic sampling method initialization background;
The described present frame that obtains and background frames carry out difference, and statistics is less than 20 pixel number,, think that this point is background dot, otherwise belong to the foreground point greater than 2 the time when the pixel number of obtaining.
By as seen above-mentioned, specific embodiment of the present invention is for to detect the video camera in complex scene, further, by gathering frame of video, utilize mixed Gauss model to carry out background constructing, recycling stochastic sampling method is sampled to the random point around each pixel, and the initialization background; Then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.Realized that the video camera under the complex scene moves detection, have very high accuracy and robustness, effectively solved in complicated scene, the interference of the various extraneous factors of existence (as illumination variation, dynamic background element etc.) causes the problem of wrong report.
Therefore; easily understand, the above is only preferred embodiment of the present invention, is not be used to limiting spirit of the present invention and protection domain; the equivalent variations that any those of ordinary skill in the art make or replacement are within all should being considered as being encompassed in protection scope of the present invention.
Claims (3)
1. video camera movement detection method based on video monitoring, it is characterized in that: comprise at first gathering frame of video, utilize mixed Gauss model to carry out background constructing, recycling stochastic sampling method is sampled to the random point around each pixel, and the initialization background; Then present frame and the background frames that obtains carried out difference, statistics is less than 20 pixel number,, thinks that this point is background dot, otherwise belongs to the foreground point greater than 2 the time when the pixel number of obtaining; At last, according to the pixel number of calculating the prospect frame, by comparing to judge with a certain fixed threshold whether video camera is moved, thereby realize that video camera moves detection.
2. the video camera movement detection method based on video monitoring according to claim 1 is characterized in that: described from obtaining frame of video, and utilize mixed Gaussian to carry out background modeling, and adopt stochastic sampling method initialization background.
3. the video camera movement detection method based on video monitoring according to claim 1, it is characterized in that: carry out difference according to the described present frame that obtains and background frames, statistics is less than 20 pixel number, when the pixel number of obtaining greater than 2 the time, think that this point is background dot, otherwise belong to the foreground point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012104883404A CN103150736A (en) | 2012-11-16 | 2012-11-16 | Camera motion detecting method based on video monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012104883404A CN103150736A (en) | 2012-11-16 | 2012-11-16 | Camera motion detecting method based on video monitoring |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103150736A true CN103150736A (en) | 2013-06-12 |
Family
ID=48548789
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012104883404A Pending CN103150736A (en) | 2012-11-16 | 2012-11-16 | Camera motion detecting method based on video monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103150736A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634593A (en) * | 2013-12-23 | 2014-03-12 | 深圳市捷顺科技实业股份有限公司 | Movement detection method and system for video camera |
CN105678730A (en) * | 2014-11-17 | 2016-06-15 | 西安三茗科技有限责任公司 | Camera movement self-detecting method on the basis of image identification |
CN105960664A (en) * | 2014-02-07 | 2016-09-21 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
CN106162158A (en) * | 2015-04-02 | 2016-11-23 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device identifying lens shooting mode |
CN106686347A (en) * | 2016-11-21 | 2017-05-17 | 国电南瑞科技股份有限公司 | Video based method for judging translocation of metro camera |
CN106899793A (en) * | 2015-12-17 | 2017-06-27 | 南京视察者信息技术有限公司 | A kind of method whether real-time monitoring video camera moves |
CN110864412A (en) * | 2019-08-12 | 2020-03-06 | 珠海格力电器股份有限公司 | Air conditioner control method and system |
CN113014744A (en) * | 2019-12-19 | 2021-06-22 | 合肥君正科技有限公司 | Method for shielding monitoring picture in vehicle and eliminating light flicker interference |
CN110798681B (en) * | 2019-11-12 | 2022-02-01 | 阿波罗智联(北京)科技有限公司 | Monitoring method and device of imaging equipment and computer equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050104964A1 (en) * | 2001-10-22 | 2005-05-19 | Bovyrin Alexandr V. | Method and apparatus for background segmentation based on motion localization |
US7956889B2 (en) * | 2003-06-04 | 2011-06-07 | Model Software Corporation | Video surveillance system |
CN102629383A (en) * | 2012-02-28 | 2012-08-08 | 湖南大学 | Motion object detection method based on random strategy |
-
2012
- 2012-11-16 CN CN2012104883404A patent/CN103150736A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050104964A1 (en) * | 2001-10-22 | 2005-05-19 | Bovyrin Alexandr V. | Method and apparatus for background segmentation based on motion localization |
US7956889B2 (en) * | 2003-06-04 | 2011-06-07 | Model Software Corporation | Video surveillance system |
CN102629383A (en) * | 2012-02-28 | 2012-08-08 | 湖南大学 | Motion object detection method based on random strategy |
Non-Patent Citations (1)
Title |
---|
徐璐: "基于直方图和混合高斯模型的摄像机移动检测", 《中国优秀硕士论文全文数据库》, no. 12, 15 December 2011 (2011-12-15) * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634593A (en) * | 2013-12-23 | 2014-03-12 | 深圳市捷顺科技实业股份有限公司 | Movement detection method and system for video camera |
CN105960664A (en) * | 2014-02-07 | 2016-09-21 | 诺日士精密株式会社 | Information processing device, information processing method, and program |
CN105678730A (en) * | 2014-11-17 | 2016-06-15 | 西安三茗科技有限责任公司 | Camera movement self-detecting method on the basis of image identification |
CN106162158A (en) * | 2015-04-02 | 2016-11-23 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device identifying lens shooting mode |
CN106899793A (en) * | 2015-12-17 | 2017-06-27 | 南京视察者信息技术有限公司 | A kind of method whether real-time monitoring video camera moves |
CN106686347A (en) * | 2016-11-21 | 2017-05-17 | 国电南瑞科技股份有限公司 | Video based method for judging translocation of metro camera |
CN106686347B (en) * | 2016-11-21 | 2019-08-23 | 国电南瑞科技股份有限公司 | A method of the judgement subway camera shifting based on video |
CN110864412A (en) * | 2019-08-12 | 2020-03-06 | 珠海格力电器股份有限公司 | Air conditioner control method and system |
CN110864412B (en) * | 2019-08-12 | 2021-02-12 | 珠海格力电器股份有限公司 | Air conditioner control method and system |
CN110798681B (en) * | 2019-11-12 | 2022-02-01 | 阿波罗智联(北京)科技有限公司 | Monitoring method and device of imaging equipment and computer equipment |
CN113014744A (en) * | 2019-12-19 | 2021-06-22 | 合肥君正科技有限公司 | Method for shielding monitoring picture in vehicle and eliminating light flicker interference |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103150736A (en) | Camera motion detecting method based on video monitoring | |
CN100585656C (en) | An all-weather intelligent video analysis monitoring method based on a rule | |
CN103246896B (en) | A kind of real-time detection and tracking method of robustness vehicle | |
CN103500324B (en) | Violent behavior recognition methods based on video monitoring | |
CN102236947B (en) | Flame monitoring method and system based on video camera | |
CN104680557A (en) | Intelligent detection method for abnormal behavior in video sequence image | |
CN103226712B (en) | A kind of remnant object detection method based on finite state machine | |
CN102663362B (en) | Moving target detection method based on gray features | |
CN102063613A (en) | People counting method and device based on head recognition | |
CN113239822A (en) | Dangerous behavior detection method and system based on space-time double-current convolutional neural network | |
Li et al. | Toward efficient safety helmet detection based on YoloV5 with hierarchical positive sample selection and box density filtering | |
Liu et al. | Anomaly detection in surveillance video using motion direction statistics | |
CN104732236B (en) | A kind of crowd's abnormal behaviour intelligent detecting method based on layered shaping | |
CN103810717A (en) | Human behavior detection method and device | |
CN104866827A (en) | Method for detecting people crossing behavior based on video monitoring platform | |
CN104378604A (en) | Real-time monitoring method based on movement detection | |
CN103473533A (en) | Video motion object abnormal behavior automatic detection method | |
CN103489202A (en) | Intrusion detection method based on videos | |
CN102708573B (en) | Group movement mode detection method under complex scenes | |
CN102609685B (en) | Shadowing judging method of image type fire detector | |
CN107729811B (en) | Night flame detection method based on scene modeling | |
CN104574340A (en) | Video intrusion detection method based on historical images | |
CN103425958A (en) | Method for detecting non-movable objects in video | |
CN102789645A (en) | Multi-objective fast tracking method for perimeter precaution | |
CN101877135A (en) | Moving target detecting method based on background reconstruction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130612 |