CN104581001A - Related monitoring method for large range multiple cameras moving objects - Google Patents
Related monitoring method for large range multiple cameras moving objects Download PDFInfo
- Publication number
- CN104581001A CN104581001A CN201310475574.XA CN201310475574A CN104581001A CN 104581001 A CN104581001 A CN 104581001A CN 201310475574 A CN201310475574 A CN 201310475574A CN 104581001 A CN104581001 A CN 104581001A
- Authority
- CN
- China
- Prior art keywords
- camera
- video
- topological relation
- video camera
- algorithm
- 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
Landscapes
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
A related monitoring method for large range multiple cameras moving objects comprises the following steps: (1) when a video monitoring system is established, a deployment position of a camera is designed as required, position locating information of the camera is measured by utilizing related appendants or a GPS during installation and construction, various related parameters are recorded, and a GIS database is created; (2) the obtained position locating information of the camera and related parametric GIS data are matched with electronic map data, and a topological relation of the camera is generated by utilizing the designed topological relation generating algorithm; (3) a video intelligent monitoring algorithm and a program are operated on the base of the established camera topological relation, and video topology related monitoring is achieved.
Description
Technical field
The present invention relates to public safety video brainpower watch and control field, relate to the pass connection monitoring method of the moving target of multiple-camera on a large scale of a kind of Integrated predict model geographic information system technology, video brainpower watch and control technology.
Background technology
Along with the progress of technology and the development of society, video monitoring system obtains application in the middle of many industries, the particularly industry such as public security, security, they are born social stability maintenance, guarantee the important task of people's personal safety and property safety, have higher requirement to the performance of video monitoring system and function and expect.
Traditional video monitoring system mostly adopts multiple camera to catch picture and on electronic curtain, separates the mode of display.This mode due to the relatively independent shortage relevance of monitored picture, in public safety applications field, often can in the face of super amount camera head monitor video information, cannot realize the moving target of video brainpower watch and control from motion tracking.
Along with the development of computer information technology, video brainpower watch and control technology and geographical information technology are paid attention at public safety field and are applied, wherein the most key and important with multiple-camera target following, also be current difficult point, this is because under new application demand, the precondition that traditional video monitoring algorithm supposes no longer is set up.In order to develop comparatively ripe, stable multiple-camera target tracking algorism, need to carry out modeling comparatively accurately to camera supervised space topological and time topological structure, on this basis, carry out the exploitation of video monitoring algorithm and realize guarantee and really meet application demand preferably.
Current video monitoring system does not also extensively set up the topological relation on room and time, and effectively cannot carry out association monitoring, multiple-camera motion estimate track algorithm is also difficult to obtain desirable effect.The way setting up video camera topological relation is normally set up by hand, automatically building topological method is propose under video monitoring camera is in great demand so that artificial means are difficult to the needs situation of satisfied fast run-up topology, and way conventional at present adopts the method such as probability estimate, machine learning to realize.But these methods sometimes efficiency are still difficult to be guaranteed, mainly solving because of probability estimate and machine learning algorithm itself may be comparatively complicated, and has stronger dependence to training data.
Summary of the invention
The object of the present invention is to provide a kind of method that can realize the association monitoring of multiple-camera moving target on a large scale.In order to realize the intelligent monitoring of multiple-camera moving target on a large scale, face the problem that between video camera, how incidence relation is set up, i.e. topological relation, and the efficiency of building topology relation affects one of comparatively crucial factor of whole supervisory control system running efficiency.In order to improve the operational efficiency of whole supervisory system, need to propose brand-new algorithm according to the actual demand of multiple-camera moving target intelligent monitoring on a large scale.New algorithm should be sane, do not rely on observation data, has stronger retractility and extendability, still can ensure that system is resumed operation within a short period of time when camera quantity and infield change.
Technical solution of the present invention is as follows:
A kind of video topological correlation method for supervising, is characterized in that comprising the following steps:
(1) when video monitoring system is built, design video camera deployed position as required, in installation process, utilize associated satellite thing or utilize GPS to measure the position location information of video camera, and record every correlation parameter, set up GIS database;
(2) position location information of video camera obtained and the GIS data of correlation parameter are mated with electronic map data, utilize the Topology generation algorithm of design to generate the topological relation of video camera;
(3) on the basis of topological relation establishing video camera, run video brainpower watch and control algorithm and program, realize the monitoring of video topological correlation.
Described in above-mentioned steps (2), Topology generation algorithm is specific as follows:
(21) setting search radius r, travels through each point, searches all some p of distance within the scope of radius r of this point when traversing this;
(22) calculate current point and the direction of some p, the attribute in this direction of current point is set according to the definition in 8 directions for some p;
(23) traveled through, generate No. ID of each some point in search radius corresponding in 8 directions, topological relation has been set up.
The present invention has redesigned multiple-camera moving target intelligent-tracking policing algorithm on a large scale, proposes a kind of video topological correlation method for supervising.Geographical information technology is adopted to obtain the positional information of video camera and show in electronic chart, association analysis is carried out with camera position according to the road information in electronic chart and building information etc., determine spatial topotaxy and the temporal topological relation of adjacent camera, and automatically generate the supervision territory of camera according to the correlation parameter that video camera is laid.The modes such as nine grids can be adopted to be shown by the video be associated when monitoring, also can at running background to follow the tracks of the movement locus paying close attention to target rapidly, this Design and implementation is more conducive to the deployment of intelligent monitoring algorithm.
Present invention employs GIS data and algorithm as support, apply in monitor video video camera building topology incidence relation, thus improve video camera topological relation set up efficiency, and can be utilized effectively in video brainpower watch and control.This design enormously simplify the complexity of algorithm and improves operational efficiency and stability, makes the intelligent monitoring scheme of multi-cam on a large scale more practical.
Embodiment
Specific embodiment of the invention step is as follows:
The first, at video monitoring system first stage of construction, need to design video camera deployed position as required, in installation process, utilize associated satellite thing or utilize GPS to measure the position location information of video camera, and record every correlation parameter, set up GIS database.
The second, the position location information of video camera obtained and the GIS data of correlation parameter are mated with electronic map data, utilizes the Topology generation algorithm of design to generate the topological relation of video camera.In GIS, the topological relation of point can represent with direction, and topological relation can use GIS Software Create, also can generate by algorithm for design.The Topology generation algorithm of the point of the present invention's design is as follows:
(1) setting search radius r, travels through each point, searches all some p of distance within the scope of radius r of this point when traversing this; (2) calculate current point and the direction of some p, the attribute in this direction of current point is set according to the definition in 8 directions for some p; (3) traveled through, generate No. ID of each some point in search radius corresponding in 8 directions, topological relation has been set up.
In addition, can according to the installation parameter definition video area of video camera, this process can complete automatically, and artificial means also can be used to complete.Automatically complete and need to design corresponding implementation algorithm, the algorithm that the present invention adopts is the radius covered according to the inclination angle of video camera and high computational video camera according to the principle of triangulation, and by the direction of camera horizon scanning and the fan-shaped direction of angle restriction and angle, so far, the video monitoring range that video camera is corresponding has built.
3rd, video brainpower watch and control algorithm and program are run in the basis of topological relation establishing video camera, realizes the monitoring of video topological correlation.The algorithm of multiple-camera motion target tracking monitoring on a large scale can be divided into three parts: be first identification and the tracking to paying close attention to target, there is multiple implementation algorithm, the most simply and comparatively practical algorithm is that two two field pictures subtract each other, namely can get rid of background extracting and go out moving target, identification for the target of known features is then need the clarification of objective according to grasping to carry out the matching analysis to the key frame of video, thus finds out the camera video scope that target appears at; Next is the camera video scope occurred according to target, the contiguous camera in 8 directions is found out according to the topological relation of camera, range of video corresponding to these cameras can be assumed to next step region that may occur of target, can carry out further reducing next step range of video that may occur of target after adding road information; Finally may there is the coupling of carrying out target in the video of the camera of target at these, if the monitoring range of camera is comparatively large and under target identification and coupling are comparatively easy to prerequisite, the Intelligent target of multiple-camera is followed the tracks of and then realized on a large scale.
Claims (2)
1. a sky connection monitoring method for multiple-camera moving target on a large scale, is characterized in that comprising the following steps:
(1) when video monitoring system is built, design video camera deployed position as required, in installation process, utilize associated satellite thing or utilize GPS to measure the position location information of video camera, and record every correlation parameter, set up GIS database;
(2) position location information of video camera obtained and the GIS data of correlation parameter are mated with electronic map data, utilize the Topology generation algorithm of design to generate the topological relation of video camera;
(3) on the basis of topological relation establishing video camera, run video brainpower watch and control algorithm and program, realize the monitoring of video topological correlation.
2. the pass connection monitoring method of the moving target of multiple-camera on a large scale according to claim 1, is characterized in that, described in step (2), Topology generation algorithm is as follows:
(21) setting search radius r, travels through each point, searches all some p of distance within the scope of radius r of this point when traversing this;
(22) calculate current point and the direction of some p, the attribute in this direction of current point is set according to the definition in 8 directions for some p;
(23) traveled through, generate No. ID of each some point in search radius corresponding in 8 directions, topological relation has been set up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310475574.XA CN104581001A (en) | 2013-10-12 | 2013-10-12 | Related monitoring method for large range multiple cameras moving objects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310475574.XA CN104581001A (en) | 2013-10-12 | 2013-10-12 | Related monitoring method for large range multiple cameras moving objects |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104581001A true CN104581001A (en) | 2015-04-29 |
Family
ID=53096082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310475574.XA Pending CN104581001A (en) | 2013-10-12 | 2013-10-12 | Related monitoring method for large range multiple cameras moving objects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104581001A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105336171A (en) * | 2015-10-16 | 2016-02-17 | 浙江宇视科技有限公司 | Camera position calibration method and device |
| CN105472333A (en) * | 2015-12-04 | 2016-04-06 | 航天科工智慧产业发展有限公司 | Establishment method for topological system of video monitoring equipment and associated monitoring method |
| CN105472334A (en) * | 2015-12-04 | 2016-04-06 | 航天科工智慧产业发展有限公司 | Historical video topological correlation reviewing method |
| CN105893510A (en) * | 2016-03-30 | 2016-08-24 | 北京格灵深瞳信息技术有限公司 | Video structurization system and target search method thereof |
| CN106612414A (en) * | 2015-10-27 | 2017-05-03 | 北京航天长峰科技工业集团有限公司 | Tracking control method for suspicious target of key region video |
| CN107610505A (en) * | 2017-08-30 | 2018-01-19 | 成都臻识科技发展有限公司 | One kind is based on parking stall guiding camera instruction equipment networking, installation and locating method and device |
| CN110365943A (en) * | 2019-07-19 | 2019-10-22 | 福建恒锋电子科技有限公司 | A kind of video monitoring method and system based on character matrix large-size screen monitors |
| CN112182917A (en) * | 2020-11-30 | 2021-01-05 | 中国电力科学研究院有限公司 | Multi-objective optimization-based camera device deployment and control optimization method, system, device and storage medium |
| CN113111843A (en) * | 2021-04-27 | 2021-07-13 | 北京赛博云睿智能科技有限公司 | Remote image data acquisition method and system |
-
2013
- 2013-10-12 CN CN201310475574.XA patent/CN104581001A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105336171A (en) * | 2015-10-16 | 2016-02-17 | 浙江宇视科技有限公司 | Camera position calibration method and device |
| CN105336171B (en) * | 2015-10-16 | 2017-12-29 | 浙江宇视科技有限公司 | A kind of camera position scaling method and device |
| CN106612414A (en) * | 2015-10-27 | 2017-05-03 | 北京航天长峰科技工业集团有限公司 | Tracking control method for suspicious target of key region video |
| CN105472333A (en) * | 2015-12-04 | 2016-04-06 | 航天科工智慧产业发展有限公司 | Establishment method for topological system of video monitoring equipment and associated monitoring method |
| CN105472334A (en) * | 2015-12-04 | 2016-04-06 | 航天科工智慧产业发展有限公司 | Historical video topological correlation reviewing method |
| CN105893510A (en) * | 2016-03-30 | 2016-08-24 | 北京格灵深瞳信息技术有限公司 | Video structurization system and target search method thereof |
| CN107610505A (en) * | 2017-08-30 | 2018-01-19 | 成都臻识科技发展有限公司 | One kind is based on parking stall guiding camera instruction equipment networking, installation and locating method and device |
| CN110365943A (en) * | 2019-07-19 | 2019-10-22 | 福建恒锋电子科技有限公司 | A kind of video monitoring method and system based on character matrix large-size screen monitors |
| CN112182917A (en) * | 2020-11-30 | 2021-01-05 | 中国电力科学研究院有限公司 | Multi-objective optimization-based camera device deployment and control optimization method, system, device and storage medium |
| CN112182917B (en) * | 2020-11-30 | 2021-08-03 | 中国电力科学研究院有限公司 | Multi-objective optimization-based camera device deployment and control optimization method, system, device and storage medium |
| CN113111843A (en) * | 2021-04-27 | 2021-07-13 | 北京赛博云睿智能科技有限公司 | Remote image data acquisition method and system |
| CN113111843B (en) * | 2021-04-27 | 2023-12-29 | 北京赛博云睿智能科技有限公司 | Remote image data acquisition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104581001A (en) | Related monitoring method for large range multiple cameras moving objects | |
| Kong et al. | Efficient traffic state estimation for large-scale urban road networks | |
| Badino et al. | Visual topometric localization | |
| KR20200121274A (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| KR101856488B1 (en) | Method, apparatus and computer-readable medium for object tracking using the three-dimensional mapping | |
| Liang et al. | An automatic site survey approach for indoor localization using a smartphone | |
| Wang et al. | Keyframe based large-scale indoor localisation using geomagnetic field and motion pattern | |
| US20140164306A1 (en) | Pathway management using model analysis and forcasting | |
| CN111879305B (en) | Multi-mode perception positioning model and system for high-risk production environment | |
| CN109558831A (en) | It is a kind of fusion space-time model across camera shooting head's localization method | |
| CN109839118A (en) | Paths planning method, system, robot and computer readable storage medium | |
| CN109934074A (en) | Movement track determines method and device | |
| Heydarian et al. | A visual monitoring framework for integrated productivity and carbon footprint control of construction operations | |
| Abbate et al. | Prospective upon multi-source urban scale data for 3d documentation and monitoring of urban legacies | |
| CN116091039A (en) | Power transmission and transformation project acceptance result visualization method and system based on south network intelligent aerial view | |
| CN114615740A (en) | Indoor personnel positioning method based on Bluetooth, PDR and map matching fusion | |
| Prentow et al. | Making sense of trajectory data in indoor spaces | |
| CN105472333A (en) | Establishment method for topological system of video monitoring equipment and associated monitoring method | |
| Fang et al. | CityTracker: Citywide individual and crowd trajectory analysis using hidden Markov model | |
| Li et al. | An efficient point cloud place recognition approach based on transformer in dynamic environment | |
| Prentow et al. | Estimating common pedestrian routes through indoor path networks using position traces | |
| Wang et al. | Hybrid RFID system-based pedestrian localization: A case study | |
| CA2894863A1 (en) | Indoor localization using crowdsourced data | |
| Siddiqui | UWB RTLS for construction equipment localization: experimental performance analysis and fusion with video data | |
| CN105898191A (en) | Video topological correlation monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150429 |