CN104794459A - Video personnel identification method - Google Patents
Video personnel identification method Download PDFInfo
- Publication number
- CN104794459A CN104794459A CN201510227266.4A CN201510227266A CN104794459A CN 104794459 A CN104794459 A CN 104794459A CN 201510227266 A CN201510227266 A CN 201510227266A CN 104794459 A CN104794459 A CN 104794459A
- Authority
- CN
- China
- Prior art keywords
- personnel
- image information
- face
- information
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A video personnel identification method includes establishing a personnel image information registration database; according to the walking trace of an identified person, acquiring monitoring video data of different video monitoring points; acquiring the personnel image information of the identified person according to one frame or multiple continuous frames of the monitoring video data images; according to an image frame fuzzy threshold, acquiring image frames larger than the threshold, and extracting the personnel image information of the identified person according to the acquired image frames; comparing the extracted multiple frame image information comprehensively, and selecting optimal image information to combine so as to acquire final extracted personnel image information; submitting the final extracted personnel image information to a face registration database to compare or register and store. The method has the advantages that the defects that according to the prior art, the personnel identification error rate is high, efficiency is low and persons with changed clothes or shielded faces cannot be identified are solved.
Description
Technical field
The invention belongs to field of face identification, particularly relate to a kind of method of carrying out personnel identity judgement from video.
Background technology
The study hotspot of artificial intelligence field is not only in recognition of face, and at public safety field, its research also has important realistic meaning.
Along with the development of technology, current public place is generally all provided with video monitoring equipment, monitors public safety with this.In current field of video monitoring, traditional cameras gradually replace by the built-in network video camera of a new generation.For traditional cameras, web camera can convert analog video signal to digital video signal, realizes remote monitoring by network.For recognition of face, video monitoring is some features utilizing face, and such as face feature identifies face.
Existing recognition of face mode is by the data analysis to single video point, there is the defect that recognition efficiency is low and error is high.Simultaneously, there is larger limitation in existing recognition of face mode, for same people, after it changes the outfit or face carries out make-up and modification process, cannot carry out recognizing and identifying, particularly for the public safety field needing to prevent trouble before it happens, when needs carry out Tracking Recognition identity to suspicious one's share of expenses for a joint undertaking, existing technology cannot carry out identifying and locating after it changes the outfit or face blocks.
Summary of the invention
The present invention be directed to the deficiencies in the prior art, propose a kind of method of carrying out personnel identity judgement from video, this method solve high, the inefficient defect of personnel identity judgement mistake that prior art exists.
A kind of method of carrying out personnel identity judgement from video of the present invention, comprising:
Set up personnel's image synthesis information registering storehouse;
According to the run trace being judged personnel, obtain the monitor video data of multiple different video monitoring point;
Obtain a frame or the estimative personnel's image information of continuous multiple frames in monitor video data plot picture frame;
According to the fuzzy threshold values of picture frame, obtain the picture frame higher than threshold values, and extract estimative personnel's image information according to the picture frame obtained;
The comprehensive multiple image information comparing mutually extraction, chooses optimum image information and is mutually combined to form the final personnel's image information extracted;
The final personnel's image information extracted is submitted in face registration storehouse carries out registration storage and comparison;
Described personnel's image information comprises face essential information, human face posture information and other characteristic informations; Described face essential information is the profile information of eyes, nose and face; Described human face posture information is: carry out extraction and analysis to the attitude of human face photo, comprises the new line of face or bows, deflects and rotate; Whether whether other described characteristic informations comprise sex, the colour of skin, wear glasses, wear masks, hair style, expression, the age, interpupillary distance, height, body weight and clothes, trousers and shoes color.
Further, described personnel's image information together with temporal information and positional information simultaneously stored in background data base.
Further, when described face deflection angle exceedes certain angle, this human face photo and face registration storehouse, backstage will not be compared.
Technical scheme of the present invention is compared to the volume beneficial effect of conventional art means: process the video data of different location, obtain and be judged the face essential information of personnel identity, human face posture information and other characteristic informations in interior various features information, effectively can eliminate the situation of erroneous judgement, misjudgement, also can avoid because same ambient image information extraction is single; By the personnel's image information analyzing multiple different location is also extracted respectively, then mutually compare optimize optimum personnel's combining image information by extracting result, technician can utilize this group optimum image information combination to the accurate identification being judged personnel and carrying out in any environment.
Embodiment
A kind of overall step of carrying out the method for personnel identity judgement from video of the present invention is:
According to the run trace being judged personnel, obtain the monitor video data of multiple different video monitoring point; Obtain a frame or the estimative personnel's image information of continuous multiple frames in monitor video data plot picture frame; According to the fuzzy threshold values of picture frame, obtain the picture frame higher than threshold values, and extract estimative personnel's image information according to the picture frame obtained; The comprehensive multiple image information comparing mutually extraction, chooses optimum image information and is mutually combined to form the final personnel's image information extracted; The final personnel's image information extracted is submitted to face identification system and carries out storing and comparison.
Described personnel's image information comprises face essential information, human face posture information and other characteristic informations; Described face essential information is the profile information of eyes, nose and face; Described human face posture information is: carry out extraction and analysis to the attitude of human face photo, comprises the new line of face or bows, deflects and rotate; Whether whether other described characteristic informations comprise sex, the colour of skin, wear glasses, wear masks, hair style, expression, the age, interpupillary distance, height, body weight and clothes, trousers and shoes color.
In implementation step of the present invention, obtaining the mode that there are the personnel that are judged in monitor video data is:
The initial image frame of video is first utilized to set up the background model of each pixel or pixel region; Foreground model is set up to pixel each in current image frame or pixel region; Calculate the difference between the background model of each pixel or pixel region and foreground model; Determine a predetermined threshold value, if the connected region producing the pixel region of difference is less than described predetermined threshold value, illustrate that current frame image does not produce movable information, face can not be there is, deletion can not produce the picture frame of face, upgrade background model, if the connected region producing the pixel region of described difference is more than or equal to described predetermined threshold value, illustrate that current frame image produces movable information, may face be there is, retain present frame and obtain described pixel region as the image-region with movable information.
Then existing recognition technology is utilized, to face essential information, human face posture information and other characteristic informations extract, the many groups personnel image information extracted is compared again, optimize the optimal value of each characteristic parameter, each most value value is carried out being combined to form new personnel's image information, then be sent to backstage personnel's image information registry compare obtaining new personnel's image information, as not relevant comparison information, then will obtain personnel's image information and carry out registering and storing at backstage human face image information registry.
Preferably, the establishing data of described human face image information registry is optimized based on Ministry of Public Security's identity card management system.
Claims (3)
1. from video, carry out a method for personnel identity judgement, it is characterized in that: the step of described method is:
Set up personnel's image synthesis information registering storehouse;
According to the run trace being judged personnel, obtain the monitor video data of multiple different video monitoring point;
Obtain a frame or the estimative personnel's image information of continuous multiple frames in monitor video data plot picture frame;
According to the fuzzy threshold values of picture frame, obtain the picture frame higher than threshold values, and extract estimative personnel's image information according to the picture frame obtained;
The comprehensive multiple image information comparing mutually extraction, chooses optimum image information and is mutually combined to form the final personnel's image information extracted;
The final personnel's image information extracted is submitted in face registration storehouse carries out registration storage and comparison;
Described personnel's image information comprises face essential information, human face posture information and other characteristic informations; Described face essential information is the profile information of eyes, nose and face; Described human face posture information is: carry out extraction and analysis to the attitude of human face photo, comprises the new line of face or bows, deflects and rotate; Whether whether other described characteristic informations comprise sex, the colour of skin, wear glasses, wear masks, hair style, expression, the age, interpupillary distance, height, body weight and clothes, trousers and shoes color.
2. a kind of method of carrying out personnel identity judgement from video as claimed in claim 1, is characterized in that: described personnel's image information together with temporal information and positional information simultaneously stored in background data base.
3. from video, carry out a method for personnel identity judgement, it is characterized in that: when described face deflection angle exceedes certain angle, this human face photo and face registration storehouse, backstage will not be compared.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510227266.4A CN104794459A (en) | 2015-05-07 | 2015-05-07 | Video personnel identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510227266.4A CN104794459A (en) | 2015-05-07 | 2015-05-07 | Video personnel identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104794459A true CN104794459A (en) | 2015-07-22 |
Family
ID=53559246
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510227266.4A Pending CN104794459A (en) | 2015-05-07 | 2015-05-07 | Video personnel identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104794459A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105931405A (en) * | 2015-12-18 | 2016-09-07 | 许昌学院 | Intelligent area security method |
CN108009523A (en) * | 2017-12-23 | 2018-05-08 | 江铃汽车股份有限公司 | Clerk's localization method, device, mobile terminal and storage medium |
CN108062404A (en) * | 2017-12-28 | 2018-05-22 | 奇酷互联网络科技(深圳)有限公司 | Processing method, device, readable storage medium storing program for executing and the terminal of facial image |
CN108269333A (en) * | 2018-01-08 | 2018-07-10 | 平安科技(深圳)有限公司 | Face identification method, application server and computer readable storage medium |
CN109002744A (en) * | 2017-06-06 | 2018-12-14 | 中兴通讯股份有限公司 | Image-recognizing method, device and video monitoring equipment |
CN109815820A (en) * | 2018-12-26 | 2019-05-28 | 深圳市天彦通信股份有限公司 | Object localization method and relevant apparatus |
WO2020094091A1 (en) * | 2018-11-07 | 2020-05-14 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera, and monitoring system |
CN112565863A (en) * | 2020-11-26 | 2021-03-26 | 深圳Tcl新技术有限公司 | Video playing method and device, terminal equipment and computer readable storage medium |
CN112565863B (en) * | 2020-11-26 | 2024-07-05 | 深圳Tcl新技术有限公司 | Video playing method, device, terminal equipment and computer readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101515324A (en) * | 2009-01-21 | 2009-08-26 | 上海银晨智能识别科技有限公司 | Control system applied to multi-pose face recognition and a method thereof |
CN101681428A (en) * | 2007-05-30 | 2010-03-24 | 伊斯曼柯达公司 | Composite person model from image collection |
CN103530648A (en) * | 2013-10-14 | 2014-01-22 | 四川空港知觉科技有限公司 | Face recognition method based on multi-frame images |
US20140079297A1 (en) * | 2012-09-17 | 2014-03-20 | Saied Tadayon | Application of Z-Webs and Z-factors to Analytics, Search Engine, Learning, Recognition, Natural Language, and Other Utilities |
CN104008370A (en) * | 2014-05-19 | 2014-08-27 | 清华大学 | Video face identifying method |
CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
-
2015
- 2015-05-07 CN CN201510227266.4A patent/CN104794459A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101681428A (en) * | 2007-05-30 | 2010-03-24 | 伊斯曼柯达公司 | Composite person model from image collection |
CN101515324A (en) * | 2009-01-21 | 2009-08-26 | 上海银晨智能识别科技有限公司 | Control system applied to multi-pose face recognition and a method thereof |
US20140079297A1 (en) * | 2012-09-17 | 2014-03-20 | Saied Tadayon | Application of Z-Webs and Z-factors to Analytics, Search Engine, Learning, Recognition, Natural Language, and Other Utilities |
CN103530648A (en) * | 2013-10-14 | 2014-01-22 | 四川空港知觉科技有限公司 | Face recognition method based on multi-frame images |
CN104008370A (en) * | 2014-05-19 | 2014-08-27 | 清华大学 | Video face identifying method |
CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105931405A (en) * | 2015-12-18 | 2016-09-07 | 许昌学院 | Intelligent area security method |
CN109002744A (en) * | 2017-06-06 | 2018-12-14 | 中兴通讯股份有限公司 | Image-recognizing method, device and video monitoring equipment |
CN108009523A (en) * | 2017-12-23 | 2018-05-08 | 江铃汽车股份有限公司 | Clerk's localization method, device, mobile terminal and storage medium |
CN108062404A (en) * | 2017-12-28 | 2018-05-22 | 奇酷互联网络科技(深圳)有限公司 | Processing method, device, readable storage medium storing program for executing and the terminal of facial image |
CN108269333A (en) * | 2018-01-08 | 2018-07-10 | 平安科技(深圳)有限公司 | Face identification method, application server and computer readable storage medium |
WO2020094091A1 (en) * | 2018-11-07 | 2020-05-14 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera, and monitoring system |
CN111163259A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera and monitoring system |
CN109815820A (en) * | 2018-12-26 | 2019-05-28 | 深圳市天彦通信股份有限公司 | Object localization method and relevant apparatus |
CN112565863A (en) * | 2020-11-26 | 2021-03-26 | 深圳Tcl新技术有限公司 | Video playing method and device, terminal equipment and computer readable storage medium |
CN112565863B (en) * | 2020-11-26 | 2024-07-05 | 深圳Tcl新技术有限公司 | Video playing method, device, terminal equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104794459A (en) | Video personnel identification method | |
CN108921100B (en) | Face recognition method and system based on visible light image and infrared image fusion | |
CN104794458A (en) | Fuzzy video person identifying method | |
CN104951773B (en) | A kind of real-time face recognition monitoring system | |
KR101215948B1 (en) | Image information masking method of monitoring system based on face recognition and body information | |
CN106650671A (en) | Human face identification method, apparatus and system | |
CN105022999A (en) | Man code company real-time acquisition system | |
CN105138954A (en) | Image automatic screening, query and identification system | |
CN106355154B (en) | Method for detecting frequent passing of people in surveillance video | |
CN103985172A (en) | An access control system based on three-dimensional face identification | |
CN107844764B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN107862240A (en) | A kind of face tracking methods of multi-cam collaboration | |
CN106251363A (en) | A kind of wisdom gold eyeball identification artificial abortion's demographic method and device | |
CN113221767B (en) | Method for training living body face recognition model and recognizing living body face and related device | |
CN114894337B (en) | Temperature measurement method and device for outdoor face recognition | |
CN113657195A (en) | Face image recognition method, face image recognition equipment, electronic device and storage medium | |
CN110175553B (en) | Method and device for establishing feature library based on gait recognition and face recognition | |
CN109101925A (en) | Biopsy method | |
CN104978734B (en) | The extracting method and device of foreground image | |
CN114898402A (en) | Pedestrian re-identification method, device and medium fusing human face and human body characteristics | |
US9286707B1 (en) | Removing transient objects to synthesize an unobstructed image | |
CN110321781B (en) | Signal processing method and device for non-contact measurement | |
WO2022134916A1 (en) | Identity feature generation method and device, and storage medium | |
CN109214354B (en) | Dynamic face retrieval and identification method based on 3D camera | |
CN109145855A (en) | A kind of method for detecting human face and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150722 |
|
WD01 | Invention patent application deemed withdrawn after publication |