CN104794458A - Fuzzy video person identifying method - Google Patents
Fuzzy video person identifying method Download PDFInfo
- Publication number
- CN104794458A CN104794458A CN201510227260.7A CN201510227260A CN104794458A CN 104794458 A CN104794458 A CN 104794458A CN 201510227260 A CN201510227260 A CN 201510227260A CN 104794458 A CN104794458 A CN 104794458A
- Authority
- CN
- China
- Prior art keywords
- face
- information
- personnel
- video
- image
- 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 fuzzy video person identifying method includes extracting face and other human body characteristic information of different places and times to form optimal whole body image information, and identifying the identity of a person by comparing the whole body image information with an authentic image information registration database. Compared with the prior art, according to the technical scheme, the method has the advantages that the technical defects of the prior art that the persons cannot be identified in fuzzy videos are solved, and the timeliness of identification is improved by optimizing the database; in addition, according to the information that a target person appears in the video possibly, the fuzzy retrieval and identification can be performed.
Description
Technical field
The invention belongs to field of face identification, particularly relate to a kind of method of carrying out personal identification from very fuzzy 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.
In some cases, be subject to the impression of the factors such as light, environment and distance, facial image in video is very fuzzy, be difficult to carry out face extraction from video, even if or can Face datection be carried out from video but face is less than the situation of 40*40 pixel time, be difficult to distinguish face feature, and then the identification of personnel identity cannot be carried out.
And existing technology not yet proposes a kind of rationally effective solution.
Summary of the invention
The present invention be directed to the deficiencies in the prior art, propose a kind of method of carrying out personal identification from fuzzy video, efficiently solving prior art can not the technological deficiency of personnel identity in resolution smearing image.
A kind of method identifying personnel from fuzzy video of the present invention, comprising:
Set up personnel's image information registry, described registry comprises the essential information of personnel;
Face datection is carried out to the picture frame in selected video, the face occurred in picture frame is extracted;
Pedestrian's track judges, obtains the picture frame of the multiple video point of same a group traveling together, extracts in picture frame with the face of a group traveling together and whole body images simultaneously;
Judge multiple face blur leveles of the same a group traveling together obtained, selected optimum face picture, extracts the face characteristic in optimum face picture;
Carry out face posture feature extraction to multiple faces of the same a group traveling together obtained, the face posture feature of extraction comprises the new line of face, bows, deflects, rotates, expresses one's feelings;
Feature extraction is carried out to multiple whole body images of the same a group traveling together obtained, and Comprehensive Correlation is carried out to the feature extracted, obtain optimum non-face characteristics of image, whether whether described non-face characteristics of image comprise sex, the colour of skin, wear glasses, wear masks, express one's feelings, hair style, the age, interpupillary distance, height, body weight, clothes color, trousers color, shoes color;
Combine and form systemic features information with the face characteristic information of a group traveling together, face posture characteristic information and non-face image feature information;
Systemic features information and personnel's image information registry contrast, and confirm personnel identity.
Further, described systemic features information also comprises location information and the temporal information of video capture.
Further, described personnel's image information registry is true and accurate personnel characteristics information.
Further, before described systemic features information and personnel's image information registry contrast, personnel's image information registry is optimized retrieval to form preliminary search face template according to the face characteristic information in systemic features information, then uses preliminary search face template and systemic features information to contrast.
Further, extract human face photo and whole body images information from video frame image before, first image enhancement processing is carried out to human face photo and whole body images information.
Further, extract human face photo and whole body images information from video frame image before, first 3D modeling process is carried out to human face photo and whole body images information.
Technical scheme of the present invention is compared to the beneficial effect of conventional art means: solve the technological deficiency that prior art can not be determined the personnel identity in fuzzy video; Simultaneously by the optimization to database, improve the ageing of personnel identity validation of information; In addition, the information that may be able to occur in video according to target person, carries out fuzzy search and identity validation.
Embodiment
Of the present inventionly a kind ofly from fuzzy video, identify that the method for personnel is by extracting different location and the face of time and other characteristic informations of health to form optimum whole body images information, then utilizing whole body images information and genuine and believable personnel's image information registry to carry out contrast to confirm personnel identity.Meanwhile, utilize technical solutions according to the invention, by the optimization of database and the adjustment of way of contrast, the several non-face characteristic information that may be able to be carried by goal task, as clothes color, the place of the colour of skin, appearance and temporal information etc., can judge the identity of goal task.
Described a kind ofly from fuzzy video, identify that the method specific implementation process of personnel is: set up personnel's image information registry, described registry comprises the essential information of personnel; Face datection is carried out to the picture frame in selected video, the face occurred in picture frame is extracted; Pedestrian's track judges, obtains the picture frame of the multiple video point of same a group traveling together, extracts in picture frame with the face of a group traveling together and whole body images simultaneously; Judge multiple face blur leveles of the same a group traveling together obtained, selected optimum face picture, extracts the face characteristic in optimum face picture; Carry out face posture feature extraction to multiple faces of the same a group traveling together obtained, the face posture feature of extraction comprises the new line of face, bows, deflects, rotates, expresses one's feelings; Feature extraction is carried out to multiple whole body images of the same a group traveling together obtained, and Comprehensive Correlation is carried out to the feature extracted, obtain optimum non-face characteristics of image, whether whether described non-face characteristics of image comprise sex, the colour of skin, wear glasses, wear masks, express one's feelings, hair style, the age, interpupillary distance, height, body weight, clothes color, trousers color, shoes color; Combine and form systemic features information with the face characteristic information of a group traveling together, face posture characteristic information and non-face image feature information; Systemic features information and personnel's image information registry contrast, and confirm personnel identity.
Before the face characteristic in video frame image is extracted, face picture information to be extracted can be optimized by image enhancement technique or 3D modeling technique.
Personnel's image information registry of the present invention comprises following accurately real information: the information such as name, identification card number, passport No., former name, institute's license plate number of driving, native place, I.D. hair style address, masterpiece, sex, height, body weight, marital status, educational background, work unit, phone, deposit card information, credit card information, the last communication location of phone, identity card picture, nearest face photograph, clothes color array.
It should be noted that, the technological means realizing above-mentioned technique effect is not unique, namely be not unique to the optimization of database, according to actual needs with known target person characteristic information, different optimal way can form different retrieval templates and searched targets.
Before video information data being carried out to face contrast search, can first operate video data and optimize, such as can be optimized according to target person characteristic information roughly, as the locations and regions that target person occurs, the information such as time period.
After face contrast search is carried out to video image frame information, in the information that may occur in video according to other target persons, database restriction operation is carried out, such as according to the information such as clothes color, trousers color, shoes color, height, body weight, hair style of target person to the data structure after face contrast coupling.Namely so-called restriction operation only operates the data acquisition containing some characteristic informations.
Claims (6)
1. from fuzzy video, identify a personnel's method, it is characterized in that:
Set up personnel's image information registry, described registry comprises the essential information of personnel;
Face datection is carried out to the picture frame in selected video, the face occurred in picture frame is extracted;
Pedestrian's track judges, obtains the picture frame of the multiple video point of same a group traveling together, extracts in picture frame with the face of a group traveling together and whole body images simultaneously;
Judge multiple face blur leveles of the same a group traveling together obtained, selected optimum face picture, extracts the face characteristic in optimum face picture;
Carry out face posture feature extraction to multiple faces of the same a group traveling together obtained, the face posture feature of extraction comprises the new line of face, bows, deflects, rotates, expresses one's feelings;
Feature extraction is carried out to multiple whole body images of the same a group traveling together obtained, and Comprehensive Correlation is carried out to the feature extracted, obtain optimum non-face characteristics of image, whether whether described non-face characteristics of image comprise sex, the colour of skin, wear glasses, wear masks, express one's feelings, hair style, the age, interpupillary distance, height, body weight, clothes color, trousers color, shoes color;
Combine and form systemic features information with the face characteristic information of a group traveling together, face posture characteristic information and non-face image feature information;
Systemic features information and personnel's image information registry contrast, and confirm personnel identity.
2. a kind of method identifying personnel from fuzzy video as claimed in claim 1, it is characterized in that, described systemic features information also comprises location information and the temporal information of video capture.
3. a kind of method identifying personnel from fuzzy video as claimed in claim 1, it is characterized in that, described personnel's image information registry is true and accurate personnel characteristics information.
4. a kind of method identifying personnel from fuzzy video as claimed in claim 1, it is characterized in that, before described systemic features information and personnel's image information registry contrast, personnel's image information registry is optimized retrieval to form preliminary search face template according to the face characteristic information in systemic features information, then uses preliminary search face template and systemic features information to contrast.
5. a kind of method identifying personnel from fuzzy video as claimed in claim 1, is characterized in that, before extracting human face photo and whole body images information, first carry out image enhancement processing to human face photo and whole body images information from video frame image.
6. a kind of method identifying personnel from fuzzy video as claimed in claim 1, is characterized in that, before extracting human face photo and whole body images information, first carry out 3D modeling process to human face photo and whole body images information from video frame image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510227260.7A CN104794458A (en) | 2015-05-07 | 2015-05-07 | Fuzzy video person identifying method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510227260.7A CN104794458A (en) | 2015-05-07 | 2015-05-07 | Fuzzy video person identifying method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104794458A true CN104794458A (en) | 2015-07-22 |
Family
ID=53559245
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510227260.7A Pending CN104794458A (en) | 2015-05-07 | 2015-05-07 | Fuzzy video person identifying method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104794458A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893963A (en) * | 2016-03-31 | 2016-08-24 | 南京邮电大学 | Method for screening out optimal easily-recognizable frame of single pedestrian target in video |
CN106586731A (en) * | 2016-12-30 | 2017-04-26 | 移康智能科技(上海)股份有限公司 | Visitor identifying system and method and cat eye |
CN106657069A (en) * | 2016-12-24 | 2017-05-10 | 深圳云天励飞技术有限公司 | Image data processing system |
CN106845385A (en) * | 2017-01-17 | 2017-06-13 | 腾讯科技(上海)有限公司 | The method and apparatus of video frequency object tracking |
CN107145865A (en) * | 2017-05-08 | 2017-09-08 | 温州立地电子有限公司 | A kind of system for face identity authentication |
CN107292240A (en) * | 2017-05-24 | 2017-10-24 | 深圳市深网视界科技有限公司 | It is a kind of that people's method and system are looked for based on face and human bioequivalence |
CN107770487A (en) * | 2017-09-12 | 2018-03-06 | 深圳英飞拓科技股份有限公司 | A kind of feature extraction and preferable method, system and terminal device |
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 |
CN108038473A (en) * | 2017-12-28 | 2018-05-15 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN108197608A (en) * | 2018-02-01 | 2018-06-22 | 广州市君望机器人自动化有限公司 | Face identification method, device, robot and storage medium |
CN108197318A (en) * | 2018-02-01 | 2018-06-22 | 广州市君望机器人自动化有限公司 | Face identification method, device, robot and storage medium |
CN108319916A (en) * | 2018-02-01 | 2018-07-24 | 广州市君望机器人自动化有限公司 | Face identification method, device, robot and storage medium |
CN108805140A (en) * | 2018-05-23 | 2018-11-13 | 国政通科技股份有限公司 | A kind of feature rapid extracting method and face identification system based on LBP |
CN109426787A (en) * | 2017-08-31 | 2019-03-05 | 杭州海康威视数字技术股份有限公司 | A kind of human body target track determines method and device |
CN111353438A (en) * | 2020-03-02 | 2020-06-30 | 成都三零凯天通信实业有限公司 | AI-based public place emergency medical person searching method |
CN111429476A (en) * | 2019-01-09 | 2020-07-17 | 杭州海康威视系统技术有限公司 | Method and device for determining action track of target person |
CN111523473A (en) * | 2020-04-23 | 2020-08-11 | 北京百度网讯科技有限公司 | Mask wearing identification method, device, equipment and readable storage medium |
CN111898515A (en) * | 2020-07-24 | 2020-11-06 | 北京灵汐科技有限公司 | Method and device for identifying identity of pedestrian |
CN113159632A (en) * | 2021-05-06 | 2021-07-23 | 重庆国科应用技术研究所有限公司 | Building management method and system based on user portrait |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101140620A (en) * | 2007-10-16 | 2008-03-12 | 上海博航信息科技有限公司 | Human face recognition system |
CN101226597A (en) * | 2007-01-18 | 2008-07-23 | 中国科学院自动化研究所 | Method and system for recognizing nights pedestrian based on thermal infrared gait |
CN101300588A (en) * | 2005-10-31 | 2008-11-05 | 伊斯曼柯达公司 | Determining a particular person from a collection |
CN101404094A (en) * | 2008-11-28 | 2009-04-08 | 中国电信股份有限公司 | Video monitoring and warning method and system |
CN101681428A (en) * | 2007-05-30 | 2010-03-24 | 伊斯曼柯达公司 | Composite person model from image collection |
CN102375970A (en) * | 2010-08-13 | 2012-03-14 | 北京中星微电子有限公司 | Identity authentication method based on face and authentication apparatus thereof |
CN103258191A (en) * | 2013-05-15 | 2013-08-21 | 苏州福丰科技有限公司 | Community access control system based on face recognition |
CN103516682A (en) * | 2012-06-19 | 2014-01-15 | Tcl集团股份有限公司 | Identity authentication method based on face tracking, system and television |
CN103606093A (en) * | 2013-10-28 | 2014-02-26 | 燕山大学 | Intelligent chain VIP customer service system based on human characteristics |
CN104091176A (en) * | 2014-07-18 | 2014-10-08 | 吴建忠 | Technology for applying figure and head portrait comparison to videos |
-
2015
- 2015-05-07 CN CN201510227260.7A patent/CN104794458A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101300588A (en) * | 2005-10-31 | 2008-11-05 | 伊斯曼柯达公司 | Determining a particular person from a collection |
CN101226597A (en) * | 2007-01-18 | 2008-07-23 | 中国科学院自动化研究所 | Method and system for recognizing nights pedestrian based on thermal infrared gait |
CN101681428A (en) * | 2007-05-30 | 2010-03-24 | 伊斯曼柯达公司 | Composite person model from image collection |
CN101140620A (en) * | 2007-10-16 | 2008-03-12 | 上海博航信息科技有限公司 | Human face recognition system |
CN101404094A (en) * | 2008-11-28 | 2009-04-08 | 中国电信股份有限公司 | Video monitoring and warning method and system |
CN102375970A (en) * | 2010-08-13 | 2012-03-14 | 北京中星微电子有限公司 | Identity authentication method based on face and authentication apparatus thereof |
CN103516682A (en) * | 2012-06-19 | 2014-01-15 | Tcl集团股份有限公司 | Identity authentication method based on face tracking, system and television |
CN103258191A (en) * | 2013-05-15 | 2013-08-21 | 苏州福丰科技有限公司 | Community access control system based on face recognition |
CN103606093A (en) * | 2013-10-28 | 2014-02-26 | 燕山大学 | Intelligent chain VIP customer service system based on human characteristics |
CN104091176A (en) * | 2014-07-18 | 2014-10-08 | 吴建忠 | Technology for applying figure and head portrait comparison to videos |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893963A (en) * | 2016-03-31 | 2016-08-24 | 南京邮电大学 | Method for screening out optimal easily-recognizable frame of single pedestrian target in video |
CN105893963B (en) * | 2016-03-31 | 2019-03-08 | 南京邮电大学 | A kind of method of the best frame easy to identify of single pedestrian target in screening video |
CN106657069A (en) * | 2016-12-24 | 2017-05-10 | 深圳云天励飞技术有限公司 | Image data processing system |
CN106586731A (en) * | 2016-12-30 | 2017-04-26 | 移康智能科技(上海)股份有限公司 | Visitor identifying system and method and cat eye |
CN106586731B (en) * | 2016-12-30 | 2019-09-20 | 移康智能科技(上海)股份有限公司 | A kind of visitor's identifying system, method and a kind of opal |
CN106845385A (en) * | 2017-01-17 | 2017-06-13 | 腾讯科技(上海)有限公司 | The method and apparatus of video frequency object tracking |
CN107145865A (en) * | 2017-05-08 | 2017-09-08 | 温州立地电子有限公司 | A kind of system for face identity authentication |
CN107292240A (en) * | 2017-05-24 | 2017-10-24 | 深圳市深网视界科技有限公司 | It is a kind of that people's method and system are looked for based on face and human bioequivalence |
CN107292240B (en) * | 2017-05-24 | 2020-09-18 | 深圳市深网视界科技有限公司 | Person finding method and system based on face and body recognition |
CN109426787A (en) * | 2017-08-31 | 2019-03-05 | 杭州海康威视数字技术股份有限公司 | A kind of human body target track determines method and device |
US11157720B2 (en) | 2017-08-31 | 2021-10-26 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and device for determining path of human target |
CN107770487A (en) * | 2017-09-12 | 2018-03-06 | 深圳英飞拓科技股份有限公司 | A kind of feature extraction and preferable method, system and terminal device |
CN107770487B (en) * | 2017-09-12 | 2020-06-16 | 深圳英飞拓科技股份有限公司 | Feature extraction and optimization method, system and terminal 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 |
CN108038473A (en) * | 2017-12-28 | 2018-05-15 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN108197608A (en) * | 2018-02-01 | 2018-06-22 | 广州市君望机器人自动化有限公司 | Face identification method, device, robot and storage medium |
CN108197318A (en) * | 2018-02-01 | 2018-06-22 | 广州市君望机器人自动化有限公司 | Face identification method, device, robot and storage medium |
CN108319916A (en) * | 2018-02-01 | 2018-07-24 | 广州市君望机器人自动化有限公司 | Face identification method, device, robot and storage medium |
CN108805140A (en) * | 2018-05-23 | 2018-11-13 | 国政通科技股份有限公司 | A kind of feature rapid extracting method and face identification system based on LBP |
CN111429476A (en) * | 2019-01-09 | 2020-07-17 | 杭州海康威视系统技术有限公司 | Method and device for determining action track of target person |
CN111429476B (en) * | 2019-01-09 | 2023-10-20 | 杭州海康威视系统技术有限公司 | Method and device for determining action track of target person |
CN111353438A (en) * | 2020-03-02 | 2020-06-30 | 成都三零凯天通信实业有限公司 | AI-based public place emergency medical person searching method |
CN111523473A (en) * | 2020-04-23 | 2020-08-11 | 北京百度网讯科技有限公司 | Mask wearing identification method, device, equipment and readable storage medium |
CN111523473B (en) * | 2020-04-23 | 2023-09-26 | 北京百度网讯科技有限公司 | Mask wearing recognition method, device, equipment and readable storage medium |
CN111898515A (en) * | 2020-07-24 | 2020-11-06 | 北京灵汐科技有限公司 | Method and device for identifying identity of pedestrian |
CN113159632A (en) * | 2021-05-06 | 2021-07-23 | 重庆国科应用技术研究所有限公司 | Building management method and system based on user portrait |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104794458A (en) | Fuzzy video person identifying method | |
CN106874871B (en) | Living body face double-camera identification method and identification device | |
CN109271554B (en) | Intelligent video identification system and application thereof | |
CN108596041B (en) | A kind of human face in-vivo detection method based on video | |
CN104751108B (en) | Facial image identification device and facial image recognition method | |
US8379917B2 (en) | Face recognition performance using additional image features | |
CN109598242B (en) | Living body detection method | |
CN110796079A (en) | Multi-camera visitor identification method and system based on face depth features and human body local depth features | |
CN208433010U (en) | Police AR display system based on recognition of face | |
CN106446873A (en) | Face detection method and device | |
CN105022999B (en) | A kind of adjoint real-time acquisition system of people's code | |
CN106682620A (en) | Human face image acquisition method and device | |
Guo et al. | Improving face anti-spoofing by 3D virtual synthesis | |
CN104091176A (en) | Technology for applying figure and head portrait comparison to videos | |
CN104504408A (en) | Human face identification comparing method and system for realizing the method | |
CN104408780A (en) | Face recognition attendance system | |
CN109255319A (en) | For the recognition of face payment information method for anti-counterfeit of still photo | |
CN112818722A (en) | Modular dynamically configurable living body face recognition system | |
CN109544754A (en) | A kind of guard method and system based on recognition of face, computer equipment | |
CN108647621A (en) | A kind of video analysis processing system and method based on recognition of face | |
CN109101925A (en) | Biopsy method | |
Mu et al. | Resgait: The real-scene gait dataset | |
CN110175553B (en) | Method and device for establishing feature library based on gait recognition and face recognition | |
Naveen et al. | Face recognition and authentication using LBP and BSIF mask detection and elimination | |
CN103034840A (en) | Gender identification method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150722 |