CN107547865A - Trans-regional human body video frequency object tracking intelligent control method - Google Patents
Trans-regional human body video frequency object tracking intelligent control method Download PDFInfo
- Publication number
- CN107547865A CN107547865A CN201710545525.7A CN201710545525A CN107547865A CN 107547865 A CN107547865 A CN 107547865A CN 201710545525 A CN201710545525 A CN 201710545525A CN 107547865 A CN107547865 A CN 107547865A
- Authority
- CN
- China
- Prior art keywords
- target
- trans
- server
- human body
- regional
- 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
Abstract
The invention discloses a kind of trans-regional human body video frequency object tracking intelligent control method, realize the trans-regional target monitoring of camera video and tracking, single goal in detection area and multiple target motion are detected in real time, the direction of motion that mobile target in defined area with more than one, can remove video camera can also be any.Furthermore, it is possible to the number of cameras and number of targets of the method increase detection and tracking simultaneously through increase server.
Description
Technical field
The present invention relates to computer vision field, particularly one kind with computer vision to analyze people the characteristics of, Er Qieqi
Move to realize the System and method for of trans-regional human body and non-human video frequency object tracking.
Background technology
Human motion detection in decades and target following application technology achieve significant progress, also demonstrate based on meter
The method of calculation machine visual analysis can successfully imitate people to perform some specific functions, but up to now, and there has been no any
One algorithm can accomplish to meet continuous human motion detection and target following between different cameras, to realize trans-regional people
Body motion target tracking.Either human motion detection or target following, when target be in complexity scene in, its detect and
Tracking is more difficult to realize, therefore is worked at present with the human testing of digital video monitoring and target following, and still height relies on people
Work recognizes.The monitoring of particularly trans-regional human motion and target following, domestic or blank.In this context, this hair
It is bright that trans-regional target following intelligent server is developed based on high definition IP video cameras, carry out trans-regional reality for single or multiple-camera
When intelligent human-body motion detection with tracking.This intelligent server is not limited only to human motion detecting, can also pass through identical algorithms
Carry out other movement target detecting real-times and tracking.NVR records are coordinated also to carry out non real-time tracking and analysis.
The content of the invention
For overcome the deficiencies in the prior art, the present invention provides a kind of trans-regional human body video frequency object tracking intelligent monitoring side
Method, the trans-regional target monitoring of camera video and tracking are realized, the single goal in detection area and multiple target motion are carried out
Detection in real time.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of trans-regional human body video frequency object tracking intelligent control method, it is characterised in that:
Comprise the following steps:
One, by video camera shooting image stream, and upload onto the server,
Two, server process image stream, and target is extracted from image background, judge whether the target belongs to predetermined
Target classification, it is then to enter step 3;Otherwise return to step one,
Three, server carries out feature detection to the target, extracts clarification of objective, it is determined whether carries out target following, is
Then enter step 4;Otherwise return to step one,
Four, the target is tracked, while the target and the identity information to prestore are contrasted and judge whether it is the visitor authorized,
Otherwise step 5 is entered;It is to continue to track;If tracing into the target enters forbidden zone set in advance, also into step
Five,
Five, Realtime Alerts.
Target following whether is carried out in the step 3 by supervisor to be judged.
The concrete mode that the target is tracked in the step 4 is implemented by the tracking module in server, target movement
When, server triggers tracking module, tracking module is tracked according to the feature in step 3 to target.
Trans-regional human body video frequency object tracking intelligent control method according to claim 3, it is characterised in that:It is described
During tracking in step 4, server can also be by the feature and other shootings for possessing location number or geographical position
Same type clarification of objective in same type target or NVR databases that machine photographs is compared, and can be incited somebody to action after the completion of comparison
The position of the target of same characteristic features is bonded into route according to time order and function, realizes trans-regional target following.
The beneficial effects of the invention are as follows:The invention discloses a kind of trans-regional human body video frequency object tracking intelligent monitoring side
Method, the trans-regional target monitoring of camera video and tracking are realized, the single goal in detection area and multiple target motion are carried out
Detect in real time, the direction of motion that the mobile target in defined area with more than one, can remove video camera can also be any.
Furthermore, it is possible to the number of cameras and number of targets of the method increase detection and tracking simultaneously through increase server.
Brief description of the drawings
The present invention is further described with reference to the accompanying drawings and examples.
Fig. 1 is the theory diagram of the present invention.
Embodiment
Reference picture 1, the invention discloses a kind of trans-regional human body video frequency object tracking intelligent control method, including following step
Suddenly:
One, by video camera shooting image stream, and upload onto the server,
Two, server process image stream, and target is extracted from image background, judge whether the target belongs to predetermined
Target classification, it is then to enter step 3;Otherwise return to step one, the target classification is people, and certainly predetermined target classification also may be used
To be set as other classifications, the vehicle of such as animal or movement,
Three, server carries out feature detection to the target, extracts clarification of objective, it is determined whether carries out target following, is
Then enter step 4;Otherwise return to step one, it is characterized in the notable feature of object, such as size, color, translational speed, if
Carrying out target following can be judged by supervisor, can also be determined certainly by system oneself,
Four, the target is tracked, while the target and the identity information to prestore are contrasted and judge whether it is the visitor authorized,
Otherwise step 5 is entered;It is to continue to track;If tracing into the target enters forbidden zone set in advance, also into step
Five, the concrete mode for tracking the target is implemented by the tracking module in server, when target moves, server triggers tracking
Module, tracking module is tracked according to the feature in step 3 to target, during the tracking in the step 4, server
The same type that the feature extracted in step 3 can be also photographed with other video cameras for possessing location number or geographical position
Same type clarification of objective in target or NVR databases is compared, can be by the target of same characteristic features after the completion of comparison
Position is bonded into route according to time order and function, realizes trans-regional target following.
Five, Realtime Alerts.
A kind of trans-regional human body video frequency object tracking intelligent control method provided above the embodiment of the present invention, carry out
It is discussed in detail, specific case used herein is set forth to the principle and embodiment of the present invention, above example
Explanation be only intended to help understand the present invention method and its core concept;Meanwhile for those of ordinary skill in the art,
According to the thought of the present invention, there will be changes in specific embodiments and applications, in summary, in this specification
Appearance should not be construed as limiting the invention.
Claims (4)
- A kind of 1. trans-regional human body video frequency object tracking intelligent control method, it is characterised in that:Comprise the following steps:One, by video camera shooting image stream, and upload onto the server,Two, server process image stream, and target is extracted from image background, judge whether the target is to belong to predetermined target Classification, it is then to enter step 3;Otherwise return to step one,Three, server carries out feature detection to the target, extracts clarification of objective, it is determined whether carries out target following, is to enter Enter step 4;Otherwise return to step one,Four, the target is tracked, while the target and the identity information to prestore are contrasted and judge whether it is the visitor authorized, otherwise Into step 5;It is to continue to track;If tracing into the target enters forbidden zone set in advance, also into step 5,Five, Realtime Alerts.
- 2. trans-regional human body video frequency object tracking intelligent control method according to claim 1, it is characterised in that:The step Target following whether is carried out in rapid three by supervisor to be judged.
- 3. trans-regional human body video frequency object tracking intelligent control method according to claim 1, it is characterised in that:The step The concrete mode that the target is tracked in rapid four is implemented by the tracking module in server, when target moves, server triggers Tracking module, tracking module are tracked according to the feature in step 3 to target.
- 4. trans-regional human body video frequency object tracking intelligent control method according to claim 3, it is characterised in that:The step During tracking in rapid four, the feature can also be possessed location number or the video camera in geographical position by server with other Same type clarification of objective in the same type target or NVR databases that photograph is compared, can be by phase after the completion of comparison Position with the target of feature is bonded into route according to time order and function, realizes trans-regional target following.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710545525.7A CN107547865A (en) | 2017-07-06 | 2017-07-06 | Trans-regional human body video frequency object tracking intelligent control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710545525.7A CN107547865A (en) | 2017-07-06 | 2017-07-06 | Trans-regional human body video frequency object tracking intelligent control method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107547865A true CN107547865A (en) | 2018-01-05 |
Family
ID=60970552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710545525.7A Pending CN107547865A (en) | 2017-07-06 | 2017-07-06 | Trans-regional human body video frequency object tracking intelligent control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107547865A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108650485A (en) * | 2018-03-21 | 2018-10-12 | 江苏同袍信息科技有限公司 | Personnel monitoring's method and system based on image detection and wireless probe |
CN110278399A (en) * | 2018-09-29 | 2019-09-24 | 新华智云科技有限公司 | Video automatic generation method, system, equipment and storage medium are visited in a kind of sight spot |
CN110796079A (en) * | 2019-10-29 | 2020-02-14 | 深圳龙岗智能视听研究院 | Multi-camera visitor identification method and system based on face depth features and human body local depth features |
CN113139422A (en) * | 2021-03-02 | 2021-07-20 | 广州朗国电子科技有限公司 | Conference portrait shooting verification method, equipment and storage medium |
WO2021196294A1 (en) * | 2020-04-03 | 2021-10-07 | 中国科学院深圳先进技术研究院 | Cross-video person location tracking method and system, and device |
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 |
CN101854516A (en) * | 2009-04-02 | 2010-10-06 | 北京中星微电子有限公司 | Video monitoring system, video monitoring server and video monitoring method |
CN104469299A (en) * | 2014-12-02 | 2015-03-25 | 柳州市瑞蚨电子科技有限公司 | Network camera shooting device |
CN104660970A (en) * | 2013-11-25 | 2015-05-27 | 天津市天下数码视频有限公司 | Video monitoring system |
CN105208343A (en) * | 2015-09-25 | 2015-12-30 | 珠海安联锐视科技股份有限公司 | Intelligent monitoring system and method capable of being used for video monitoring device |
-
2017
- 2017-07-06 CN CN201710545525.7A patent/CN107547865A/en active Pending
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 |
CN101854516A (en) * | 2009-04-02 | 2010-10-06 | 北京中星微电子有限公司 | Video monitoring system, video monitoring server and video monitoring method |
CN104660970A (en) * | 2013-11-25 | 2015-05-27 | 天津市天下数码视频有限公司 | Video monitoring system |
CN104469299A (en) * | 2014-12-02 | 2015-03-25 | 柳州市瑞蚨电子科技有限公司 | Network camera shooting device |
CN105208343A (en) * | 2015-09-25 | 2015-12-30 | 珠海安联锐视科技股份有限公司 | Intelligent monitoring system and method capable of being used for video monitoring device |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108650485A (en) * | 2018-03-21 | 2018-10-12 | 江苏同袍信息科技有限公司 | Personnel monitoring's method and system based on image detection and wireless probe |
CN110278399A (en) * | 2018-09-29 | 2019-09-24 | 新华智云科技有限公司 | Video automatic generation method, system, equipment and storage medium are visited in a kind of sight spot |
CN110796079A (en) * | 2019-10-29 | 2020-02-14 | 深圳龙岗智能视听研究院 | Multi-camera visitor identification method and system based on face depth features and human body local depth features |
WO2021196294A1 (en) * | 2020-04-03 | 2021-10-07 | 中国科学院深圳先进技术研究院 | Cross-video person location tracking method and system, and device |
CN113139422A (en) * | 2021-03-02 | 2021-07-20 | 广州朗国电子科技有限公司 | Conference portrait shooting verification method, equipment and storage medium |
CN113139422B (en) * | 2021-03-02 | 2023-12-15 | 广州朗国电子科技股份有限公司 | Shooting verification method, equipment and storage medium for conference portrait |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108111818B (en) | Moving target actively perceive method and apparatus based on multiple-camera collaboration | |
CN107547865A (en) | Trans-regional human body video frequency object tracking intelligent control method | |
CN103761514B (en) | The system and method for recognition of face is realized based on wide-angle gunlock and many ball machines | |
CN101699862B (en) | Acquisition method of high-resolution region-of-interest image of PTZ camera | |
CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
CN103168467B (en) | The security monitoring video camera using heat picture coordinate is followed the trail of and monitoring system and method | |
US20150015787A1 (en) | Automatic extraction of secondary video streams | |
KR101788225B1 (en) | Method and System for Recognition/Tracking Construction Equipment and Workers Using Construction-Site-Customized Image Processing | |
CN101344965A (en) | Tracking system based on binocular camera shooting | |
US20100165112A1 (en) | Automatic extraction of secondary video streams | |
CN110969118B (en) | Track monitoring system and method | |
CN104378582A (en) | Intelligent video analysis system and method based on PTZ video camera cruising | |
WO2014092552A2 (en) | Method for non-static foreground feature extraction and classification | |
CN110633648B (en) | Face recognition method and system in natural walking state | |
CN107103299B (en) | People counting method in monitoring video | |
Cai et al. | Towards a practical PTZ face detection and tracking system | |
Lalonde et al. | A system to automatically track humans and vehicles with a PTZ camera | |
CN113724335B (en) | Three-dimensional target positioning method and system based on monocular camera | |
CN102737384A (en) | Automatic spherical camera tracing method | |
Singh et al. | A multi-gait dataset for human recognition under occlusion scenario | |
Xu et al. | Smart video surveillance system | |
US11044399B2 (en) | Video surveillance system | |
Xu et al. | A novel method for people and vehicle classification based on Hough line feature | |
CN109799844A (en) | A kind of the dynamic object tracing system and method for cradle head camera | |
TW201239813A (en) | Automatic tracking method for dome camera |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Wang Liangui Inventor before: Wang Liangui Inventor before: Ju Zhiyuan Inventor before: Wang Benyan Inventor before: Wang Cheng Inventor before: Wang Lian |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180105 |