CN105095891A - Human face capturing method, device and system - Google Patents
Human face capturing method, device and system Download PDFInfo
- Publication number
- CN105095891A CN105095891A CN201410184941.5A CN201410184941A CN105095891A CN 105095891 A CN105095891 A CN 105095891A CN 201410184941 A CN201410184941 A CN 201410184941A CN 105095891 A CN105095891 A CN 105095891A
- Authority
- CN
- China
- Prior art keywords
- background
- face
- information
- nature person
- label
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims description 18
- 230000033001 locomotion Effects 0.000 claims description 10
- 238000005286 illumination Methods 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 7
- 238000003909 pattern recognition Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a human face capturing method. The method comprises steps: S1, at least one piece of natural person information is acquired, wherein the natural person information comprises a human face information; S2, a label is added to a face part of the natural person; and S3, the natural person with the added label is tracked in real time. The invention also discloses a human face capturing device and a system thereof. According to the human face capturing device and the system thereof, a specified human face can be captured and tracked, and the monitoring efficiency is high.
Description
Technical field
The present invention relates to the field of video monitoring, particularly a kind of the method with face capture function, device and system thereof.
Background technology
In today that commercial competition is day by day fierce, effective commercial management has become the key factor of trade marketing success or failure.Business model progressively by traditional tradesman to the transformation of doing business having initiative, requirements at the higher level are proposed to commercial management person: within the shortest time, rapid reaction must be made to the faint change in market, and possess market foresight and save business operation cost to greatest extent, improve the rationality etc. of the science of market day-to-day operations decision-making, shopping environment comfortableness, deployment of human resources.The maximum leader of market discipline is commodity purchaser---client, how science, effectively time, analysis are spatially carried out to the volume of the flow of passengers, and make business decision timely fast, become the key of business, the success or not of retail trade marketing model.By to the quantitative statistics of Different periods passenger flow, make managerial personnel can increase staff in phase commuter rush hour, improve service quality, and then increase sale; Reduce a staff at one's leisure, avoid occurring that personnel waste.By continuous passenger flow statistics every day, one day, one week, the passenger flow Changing Pattern in January, a year can be drawn, managerial personnel accurately can be planned future activity, determine time, manpower and stock's size of order etc.
In today that world's struggle against terror is increasingly severe, people wish to occur intelligentized network video monitor and control system, can become the strong aid of reply terrorist attack and process accident, and prior art can not realize for the realization of crowded occasion to the tracking of suspect's face and seizure.
Summary of the invention
In order to solve above problem, the invention provides a kind of method of face capture function, device and system thereof, solving prior art and can not realize for the realization of crowded occasion the tracking of suspect's face and seizure.
Technical scheme of the present invention is achieved in that
The invention discloses a kind of method that face catches, comprising:
S1. obtain at least one nature person's information, described nature person's information comprises face information;
S2. at described nature person face filling label;
S3. real-time tracing has been annotated the described nature person of label.
In method of the present invention, before step S1, also there is step S0:
Set up background model, specifically: adopt the method that the background model of three-dimensional space model, mixture Gaussian background model and Corpus--based Method combines, by the space of monitoring site scene, size, colourity, pixel value is defined as can for the computerese analyzed, judge, as the basis that intelligent vision is analyzed, establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, to filter out the change of illumination, Yun Ying, leaf, wave.
In method of the present invention, described real-time tracing is specifically: split from background by region of variation from sequence image, when occurring the target of movement in guarded region, adopt BLOB algorithm and/or Fuzzy Pattern Recognition algorithm, by gray scale sudden change, moving target is distinguished from background frame, and determine its size, shape, area and accurate location.
In method of the present invention, between described step S2 and step S3, also there is step S21, adding algorithm based on the shadow removal of HSI color space and marginal information with except making an uproar.
The invention discloses the device that a kind of face catches, comprising:
Nature person's information acquisition unit, for obtaining at least one nature person's information, described nature person's information comprises face information;
Label filling unit, for label of annotating in described nature person face;
Real-time tracing unit, to have annotated the nature person described in label for real-time tracing.
In device of the present invention, before described nature person's information acquisition unit, also there is Background Modeling unit, for setting up background model, specifically: adopt three-dimensional space model, the method that the background model of mixture Gaussian background model and Corpus--based Method combines, by the space of monitoring site scene, size, colourity, pixel value is defined as can for analyzing, the computerese judged, as the basis that intelligent vision is analyzed, establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, to filter out illumination, Yun Ying, leaf, the change of wave.
In device of the present invention, described real-time tracing is specifically: split from background by region of variation from sequence image, when occurring the target of movement in guarded region, adopt BLOB algorithm and/or Fuzzy Pattern Recognition algorithm, by gray scale sudden change, moving target is distinguished from background frame, and determine its size, shape, area and accurate location.
In device of the present invention, have except unit of making an uproar between described label filling unit and real-time tracing unit, for adding algorithm based on the shadow removal of HSI color space and marginal information with except making an uproar.
The invention discloses the system that a kind of face catches, comprise at least one camera, the display terminal be connected with described camera, the controller be connected with described display terminal, described controller has the device that above-mentioned face catches.
In the systems described in the present invention, described video camera is Pan/Tilt/Zoom camera.
Implement the method for a kind of face capture function of the present invention, device and system thereof, there is following useful technique effect:
Be different from prior art and can not realize crowded district for the tracking of Given Face and seizure, the technical program can realize seizure to Given Face and tracking, and monitoring efficiency is high.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 a is the method flow diagram that a kind of face of the present invention catches;
Fig. 1 b is display first constitutional diagram that a kind of face of the present invention catches;
Fig. 1 c is display second constitutional diagram that a kind of face of the present invention catches;
Fig. 2 is the device block scheme that a kind of face of the present invention catches;
Fig. 3 is the systemic-function block scheme that a kind of face of the present invention catches.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1 a, embodiments of the invention, a kind of method that face catches, comprising:
S1. obtain at least one nature person's information, described nature person's information comprises face information;
The classification of target, identify and behavior judgement employing two-stage video analysis, one-level video analysis unit carries out the comparison of gray feature to the moving target image extracted, vicissitudinous region is formed binary image, Iamge Segmentation is carried out to the binary image formed, if the result analyzed out is less than setting, so will neglect as interference, if the result analyzed out is greater than setting, send secondary video analysis unit so immediately to, secondary video analysis unit carries out secondary analysis to this image at once, and contrast with the data in database, contrast content comprises the size of mobile image, shape, the numerical value of a series of prior regulation such as motion feature.
S2. at described nature person face filling label;
S3. real-time tracing has been annotated the described nature person of label.
Real-time tracing is specifically: split from background by region of variation from sequence image, when occurring the target of movement in guarded region, adopt BLOB algorithm and/or Fuzzy Pattern Recognition algorithm, by gray scale sudden change, moving target is distinguished from background frame, and determine its size, shape, area and accurate location.
As shown in Fig. 1 b and Fig. 1 c, the face of the band square frame in Fig. 1 b and Fig. 1 c is the suspicious object face in crowd, the second state from the first state of the monitoring Fig. 1 b to the monitoring in Fig. 1 c, the technical program can highlight a certain particular persons in crowd with accompanying as shadow, so, the technical program can be saved a large amount of manpowers and carried out searching of video and monitor, even if a certain specific personage is mixed into crowd, during track up, also be unlikely to because large contingent, be mixed into crowd, make it can not find, the track that available rectangle frame record catches, as shadow retinue, liberate human eye and stare at screen nervously for a long time, eliminate the fatigue of human eye.
Wherein, how to set up the prerequisite that accurate background model is Intelligent Measurement, it directly affects the precision of subsequent motion target detection, and the performance of the whole intelligent video analysis system of final impact and technical indicator.Background model distortion causes moving Object Segmentation unclear, thus the height to target, length, the parameter extractions such as volume are inaccurate, affect target sharpness, may affect real-time performance of tracking simultaneously.We take multiple method and define field scene, comprise: the method that the multiple background models such as the background model of three-dimensional space model, mixture Gaussian background model and Corpus--based Method combine, the space of monitoring site scene, size, colourity, pixel value etc. being defined as can for the computerese analyzed, judge.As the basis that intelligent vision is analyzed.Establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, effectively can filter out the change of the sensible factors such as illumination, Yun Ying, leaf, wave.Ensure as intelligent vision analytic unit provides true, accurate, a dynamic scene, significant to there is extremely low rate of false alarm while maintenance 99% superelevation verification and measurement ratio.
Therefore: also there is step S0 before step S1: set up background model,
Specifically: adopt the method that the background model of three-dimensional space model, mixture Gaussian background model and Corpus--based Method combines, by the space of monitoring site scene, size, colourity, pixel value is defined as can for the computerese analyzed, judge, as the basis that intelligent vision is analyzed, establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, to filter out the change of illumination, Yun Ying, leaf, wave.
Moving object detection refers to and to be split from background by region of variation from sequence image, and it is the prerequisite to target following.When occurring the target of movement in guarded region, adopting the multiple technologies such as BLOB algorithm, Fuzzy Pattern Recognition, by gray scale sudden change, moving target being distinguished from background frame, and determining its size, shape, area and accurate location etc.
This algorithm has the advantages that speed is fast, real-time is good.Simultaneously we also add the algorithm of the shadow removal based on HSI color space and marginal information, thus effectively filtering because of the impact of the many factors of the change of wave on weather, illumination, shadow, leaf swing, sea and chaotic interference etc., and overcome the impact of target because of model, outward appearance, decoration, motion etc., system is extracted and can extract moving target more exactly, set up target database: comprise the essential informations such as the size of moving target, position, shape, track.Reduce because shade exists the false-alarm caused.Even this technology is in the OV company of global Intelligent Video Surveillance Technology leading position, for there is false-alarm that the change of wave on leaf swing or sea causes in scene, wrong report problem is not also well solved.But we successfully solve the world-famous puzzle of effective detection of moving target.
Therefore, further, between described step S2 and step S3, also there is step S21, adding algorithm based on the shadow removal of HSI color space and marginal information with except making an uproar.
In the technical program, we establish target characteristic database,
The first step, sets up and " probability model of behavior such as walks, runs, jumps, climbs, squats, bends;
Second step, extracts algorithm in subordinate act model;
3rd step, implants DSP (digital signal processing), becomes embedded software by algorithm;
4th step, outdoor scene verification algorithm, allows DSP unit from pixel change learning behavior pattern and classification;
5th step, DSP algoritic module, commercialization.
Refer to the device 1 of Fig. 2, the seizure of a kind of face, for realizing above-mentioned method, the item that this device is not stated in detail, the statement in said method can be consulted, comprising:
Nature person's information acquisition unit 10, for obtaining at least one nature person's information, described nature person's information comprises face information;
Label filling unit 20, for label of annotating in described nature person face;
Real-time tracing unit 30, to have annotated the nature person described in label for real-time tracing.
Real-time tracing is specifically: split from background by region of variation from sequence image, when occurring the target of movement in guarded region, adopt BLOB algorithm and/or Fuzzy Pattern Recognition algorithm, by gray scale sudden change, moving target is distinguished from background frame, and determine its size, shape, area and accurate location.
Further, before nature person's information acquisition unit 10, also there is Background Modeling unit 5, for setting up background model, specifically: adopt three-dimensional space model, the method that the background model of mixture Gaussian background model and Corpus--based Method combines, by the space of monitoring site scene, size, colourity, pixel value is defined as can for analyzing, the computerese judged, as the basis that intelligent vision is analyzed, establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, to filter out illumination, Yun Ying, leaf, the change of wave.
Further, have except unit 25 of making an uproar between label filling unit 20 and real-time tracing unit 30, for adding algorithm based on the shadow removal of HSI color space and marginal information with except making an uproar.
Refer to Fig. 3, the system 100 that a kind of face catches, comprise at least one video camera 200, the display terminal 300 be connected with video camera 200, the controller 400 be connected with display terminal 300, controller 400 has the device 1 that above-mentioned face catches.
Video camera 200 is PTZ (overlooking/translation/zoom) video camera.
Implement the method for a kind of face capture function of the present invention, device and system thereof, there is following useful technique effect:
Be different from prior art and can not realize crowded district for the tracking of Given Face and seizure, the technical program can realize seizure to Given Face and tracking, and monitoring efficiency is high.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a method for face seizure, is characterized in that, comprising:
S1. obtain at least one nature person's information, described nature person's information comprises face information;
S2. at described nature person face filling label;
S3. real-time tracing has been annotated the described nature person of label.
2. method according to claim 1, it is characterized in that, also there is step S0 before step S1: set up background model, specifically: adopt the method that the background model of three-dimensional space model, mixture Gaussian background model and Corpus--based Method combines, by the space of monitoring site scene, size, colourity, pixel value is defined as can for the computerese analyzed, judge, as the basis that intelligent vision is analyzed, establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, to filter out the change of illumination, Yun Ying, leaf, wave.
3. method according to claim 1, it is characterized in that, described real-time tracing is specifically: split from background by region of variation from sequence image, when occurring the target of movement in guarded region, adopt BLOB algorithm and/or Fuzzy Pattern Recognition algorithm, by gray scale sudden change, moving target is distinguished from background frame, and determine its size, shape, area and accurate location.
4. method according to claim 1, is characterized in that, between described step S2 and step S3, also have step S21, adds algorithm based on the shadow removal of HSI color space and marginal information with except making an uproar.
5. a device for face seizure, is characterized in that, comprising:
Nature person's information acquisition unit, for obtaining at least one nature person's information, described nature person's information comprises face information;
Label filling unit, for label of annotating in described nature person face;
Real-time tracing unit, to have annotated the nature person described in label for real-time tracing.
6. device according to claim 5, it is characterized in that, before described nature person's information acquisition unit, also there is Background Modeling unit, for setting up background model, specifically: adopt three-dimensional space model, the method that the background model of mixture Gaussian background model and Corpus--based Method combines, by the space of monitoring site scene, size, colourity, pixel value is defined as can for analyzing, the computerese judged, as the basis that intelligent vision is analyzed, establish background simultaneously and carry out automatic learning model, in certain hour, scene is defined again, to filter out illumination, Yun Ying, leaf, the change of wave.
7. device according to claim 5, it is characterized in that, described real-time tracing is specifically: split from background by region of variation from sequence image, when occurring the target of movement in guarded region, adopt BLOB algorithm and/or Fuzzy Pattern Recognition algorithm, by gray scale sudden change, moving target is distinguished from background frame, and determine its size, shape, area and accurate location.
8. method according to claim 5, is characterized in that, has except unit of making an uproar between described label filling unit and real-time tracing unit, for adding algorithm based on the shadow removal of HSI color space and marginal information with except making an uproar.
9. the system of a face seizure, comprise at least one video camera, the display terminal be connected with described camera, the controller be connected with described display terminal, it is characterized in that, described controller has the device that the face described in any one of claim 5 to 8 catches.
10. system according to claim 9, is characterized in that, described video camera is Pan/Tilt/Zoom camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410184941.5A CN105095891A (en) | 2014-05-05 | 2014-05-05 | Human face capturing method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410184941.5A CN105095891A (en) | 2014-05-05 | 2014-05-05 | Human face capturing method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105095891A true CN105095891A (en) | 2015-11-25 |
Family
ID=54576279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410184941.5A Pending CN105095891A (en) | 2014-05-05 | 2014-05-05 | Human face capturing method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105095891A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220602A (en) * | 2017-05-18 | 2017-09-29 | 浪潮金融信息技术有限公司 | A kind of method for increasing moving region in fast Acquisition video flowing newly |
| CN109845247A (en) * | 2017-09-28 | 2019-06-04 | 京瓷办公信息系统株式会社 | Monitor terminal and display processing method |
| CN110287886A (en) * | 2019-06-26 | 2019-09-27 | 新疆大学 | A face tracking method and device |
| CN112367496A (en) * | 2020-09-09 | 2021-02-12 | 北京潞电电气设备有限公司 | Intelligent safe operation method and device for power distribution room |
| CN113412607A (en) * | 2019-06-26 | 2021-09-17 | 深圳市欢太科技有限公司 | Content pushing method and device, mobile terminal and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324024A (en) * | 2011-09-06 | 2012-01-18 | 苏州科雷芯电子科技有限公司 | A method and system for identifying and locating airport passengers based on target tracking technology |
| CN103049787A (en) * | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
-
2014
- 2014-05-05 CN CN201410184941.5A patent/CN105095891A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324024A (en) * | 2011-09-06 | 2012-01-18 | 苏州科雷芯电子科技有限公司 | A method and system for identifying and locating airport passengers based on target tracking technology |
| CN103049787A (en) * | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
Non-Patent Citations (1)
| Title |
|---|
| 赵春晖 等: "《视频图像运动目标分析》", 30 June 2011 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220602A (en) * | 2017-05-18 | 2017-09-29 | 浪潮金融信息技术有限公司 | A kind of method for increasing moving region in fast Acquisition video flowing newly |
| CN109845247A (en) * | 2017-09-28 | 2019-06-04 | 京瓷办公信息系统株式会社 | Monitor terminal and display processing method |
| CN110287886A (en) * | 2019-06-26 | 2019-09-27 | 新疆大学 | A face tracking method and device |
| CN113412607A (en) * | 2019-06-26 | 2021-09-17 | 深圳市欢太科技有限公司 | Content pushing method and device, mobile terminal and storage medium |
| CN113412607B (en) * | 2019-06-26 | 2022-09-09 | 深圳市欢太科技有限公司 | Content push method, device, mobile terminal and storage medium |
| CN112367496A (en) * | 2020-09-09 | 2021-02-12 | 北京潞电电气设备有限公司 | Intelligent safe operation method and device for power distribution room |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112396658B (en) | Indoor personnel positioning method and system based on video | |
| CN108062349B (en) | Video surveillance method and system based on video structured data and deep learning | |
| CN100585656C (en) | A rule-based all-weather intelligent video analysis and monitoring method | |
| CN103106766B (en) | Forest fire identification method and forest fire identification system | |
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| CN105426820B (en) | More people's anomaly detection methods based on safety monitoring video data | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN109298785A (en) | A man-machine joint control system and method for monitoring equipment | |
| CN101635835A (en) | Intelligent video monitoring method and system thereof | |
| CN104123544A (en) | Video analysis based abnormal behavior detection method and system | |
| CN104881643B (en) | A kind of quick remnant object detection method and system | |
| CN114708537A (en) | Multi-view-angle-based system and method for analyzing abnormal behaviors of complex places | |
| CN112329691A (en) | Monitoring video analysis method and device, electronic equipment and storage medium | |
| CN111523397A (en) | Intelligent lamp pole visual identification device, method and system and electronic equipment | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
| CN105095891A (en) | Human face capturing method, device and system | |
| CN113807467A (en) | Forest fire prevention monitoring method based on fusion analysis of optical image and infrared image | |
| CN112532927A (en) | Intelligent safety management and control system for construction site | |
| CN112188164A (en) | AI vision-based violation real-time monitoring system and method | |
| CN116416281A (en) | Grain depot AI video supervision and analysis method and system | |
| CN118277947A (en) | Outdoor photovoltaic field operation safety control method based on AI vision | |
| CN103888731A (en) | Structured description device and system for mixed video monitoring by means of gun-type camera and dome camera | |
| CN118863775A (en) | Integrated prevention and control service platform based on multi-department collaboration | |
| CN113255422A (en) | Process connection target identification management method and system based on deep learning | |
| CN108960165A (en) | A kind of stadiums population surveillance method based on intelligent video identification technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151125 |