CN103336948A - Video tracking method based on face recognition - Google Patents
Video tracking method based on face recognition Download PDFInfo
- Publication number
- CN103336948A CN103336948A CN2013102523837A CN201310252383A CN103336948A CN 103336948 A CN103336948 A CN 103336948A CN 2013102523837 A CN2013102523837 A CN 2013102523837A CN 201310252383 A CN201310252383 A CN 201310252383A CN 103336948 A CN103336948 A CN 103336948A
- Authority
- CN
- China
- Prior art keywords
- face
- teacher
- people
- tracing
- line
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a video tracking method based on face recognition. The method comprises the following steps: 1, when a teacher walks on a platform, a monitoring system detects that the teacher walks on the platform and then a tracking machine is triggered to get into a tracking mode; 2, the tracking machine performs searching through acquired points of a marginal value of the color of an image, performs connection line processing to the points and draws the outline of the head of the teacher through each connection line; 3, both the top of the head and the outline of the face of a person are found out through the connection lines and are matched with the face model preset in the tracking machine; 4, when the outline drawn by the connection lines is matched with the face model preset in the tracking machine, assisting judgment of the skin color of the face and the color of the hair is performed; if requirements are met, the judgment of a face is realized, and the teacher is tracked for shooting. The method can recognize the position of the head of the teacher according to the face recognition technology and performs shooting to the teacher through tracking, so that the close-up record of the teacher is realized, video contents are enriched, and the video effect is optimized.
Description
Technical field
The present invention discloses a kind of video tracing method, particularly a kind of video tracing method based on recognition of face.
Background technology
Along with the development of video monitoring technology, the application of video monitoring in people's sphere of life more and more widely, the application of video monitoring technology in education, medical treatment, meeting etc. is more and more.Especially in education sector, basically all camera can be installed in the classroom, be used for record classroom situation, and conventional way is, at the classroom front end camera is installed, and is used for record student situation, a camera is installed in the centre position, classroom, record teacher situation normally utilizes teacher's camera to record the panorama in zone, dais, can't realize teacher's feature record.
Summary of the invention
Can only record the shortcoming of zone, dais panorama at the above-mentioned classroom of the prior art rig camera of mentioning, the invention provides a kind of video tracing method based on recognition of face, it can identify teacher's head position according to face recognition technology, and it is carried out track up, thereby realize teacher's feature record.
The technical scheme that the present invention solves its technical matters employing is: a kind of video tracing method based on recognition of face, this method comprises the steps:
(1), be a teacher when going on the dais, supervisory system detects teacher and goes on the dais, triggers tracing machine and enters tracing mode;
(2), tracing machine searches by the point to the color edges value of the image that collects, then these points carried out link process, sketches the contours of teacher's contouring head by each line;
(3), find out people's the crown and the profile of face by these lines, mate with the faceform who is preset in the tracing machine again;
(4), the profile of sketching the contours of when line is when being preset in faceform in the tracing machine and being complementary, the colour of skin and the hair color that then further carry out people's face place carry out auxiliary judgment, if all meet the demands, namely judge and be people's face, the The Cloud Terrace that then drives tracing machine rotates and the focus of camera adjustment, teacher is carried out track up, during tracking, if one-man on the dais, then follow the tracks of this person, if a plurality of people are arranged above, then follow the tracks of the people who triggers, and seek from the nearest people of tracking target last time always.
The technical scheme that the present invention solves its technical matters employing further comprises:
Line in the described step 2 is classified according to the direction of each line, is divided into 45 degree lines, 90 degree lines, 135 degree lines and 180 degree lines.
In the described step 3 when being preset in faceform in the tracing machine and mating, the profile of sketching the contours of when line is when being preset in faceform in the tracing machine and having 80% to be complementary, then identification is people's face, continue next step operation, the profile of sketching the contours of when line be preset in faceform in the tracing machine and do not reach 80% when being complementary, then being identified as it is not people's face, returns and proceeds people's face searching and detecting.
The invention has the beneficial effects as follows: the present invention can identify teacher's head position according to face recognition technology, and it is carried out track up, thereby realizes teacher's feature record, thereby has enriched video content, has optimized video effect.
The present invention will be further described below in conjunction with the drawings and specific embodiments.
Description of drawings
Fig. 1 is process flow diagram of the present invention.
Embodiment
Present embodiment is the preferred embodiment for the present invention, and other all its principles are identical with present embodiment or approximate with basic structure, all within protection domain of the present invention.
The present invention is based on the face recognition technology to teacher, when monitoring, determine the residing position of teacher, control video camera and rotate, make teacher be in the centre position of camera lens always, teacher is continued feature take.
Please referring to accompanying drawing 1, specific implementation step of the present invention is as follows:
1, be a teacher when going on the dais, supervisory system detects teacher and goes on the dais (detection mode that adopts in the present embodiment is: by detecting the dais area image (in the present embodiment, the fixed area of the zone of detected image for arranging at the dais, this zone gets final product in the zone that teacher can be triggered to before the lectern) brightness and change color, i.e. circulation contrasts Y value and the CB of present frame and former frame, the ratio of CR value, Y value and CB when front and back two frames, the ratio of CR value is greater than a fixed coefficient (in the present embodiment, this coefficient probably is about 0.5) time, then thinking has teacher to go on the dais, and the video camera (among the present invention it being defined as tracing machine) that triggers the track up teacher enters tracing mode;
2, tracing machine by the point to the color edges value of the image that collects search (by a point (this point be on the dais any one point in being had a few judge) centered by, make progress respectively, downwards, left, search change color edge (difference of the value of y is more than 50% for 4 some cb namely and on every side, cr) to the right, be judged as change point), change point is linked up the contouring head of sketching the contours of teacher;
3, find out the profile of people's the number of people by these change point lines, (headform in the present embodiment is the outline of the number of people with being preset in headform in the tracing machine again, be the edge that the shape of the number of people is sketched the contours of with lines) mate, need have and mate be consistent (being outline line) more than 80%, when namely the profile faceform interior with being preset in tracing machine who sketches the contours of when line has 80% to be complementary, then identification is people's face, continue next step operation, the profile of sketching the contours of when line be preset in faceform in the tracing machine and beat when being complementary less than 80%, then being identified as it is not people's face, returns and proceeds people's face searching and detecting;
4, in the present embodiment, the profile of sketching the contours of when line is when being preset in faceform in the tracing machine and having 80% to be complementary, then further carry out the colour of skin at people's face place and hair color (in the present embodiment, the color of the colour of skin and hair is the CB value between 50 to 150, CR is just thinking hair and the colour of skin (in the profile scope all pixels carry out the colour of skin judge) between 100 to 200) carry out auxiliary judgment, (namely satisfying CB is 50-150 if all meet the demands, CR is 100-200), namely judge and be people's face, the The Cloud Terrace that then drives tracing machine rotates and the focus of camera adjustment, and teacher is carried out track up;
5, the tracking strategy principle in the present embodiment, if one-man on the dais then follows the tracks of this person, if above a plurality of people are arranged, the people who then follow the tracks of to trigger, and always seeking from the nearest people of tracking target last time.
The present invention can identify teacher's head position according to face recognition technology, and it is carried out track up, thereby realizes teacher's feature record, thereby has enriched video content, has optimized video effect.
Claims (3)
1. video tracing method based on recognition of face, it is characterized in that: described method comprises the steps:
(1), be a teacher when going on the dais, supervisory system detects teacher and goes on the dais, triggers tracing machine and enters tracing mode;
(2), tracing machine searches by the point to the color edges value of the image that collects, then these points carried out link process, sketches the contours of teacher's contouring head by each line;
(3), find out people's the crown and the profile of face by these lines, mate with the faceform who is preset in the tracing machine again;
(4), the profile of sketching the contours of when line is when being preset in faceform in the tracing machine and being complementary, the colour of skin and the hair color that then further carry out people's face place carry out auxiliary judgment, if all meet the demands, namely judge and be people's face, the The Cloud Terrace that then drives tracing machine rotates and the focus of camera adjustment, teacher is carried out track up, during tracking, if one-man on the dais, then follow the tracks of this person, if a plurality of people are arranged above, then follow the tracks of the people who triggers, and seek from the nearest people of tracking target last time always.
2. the video tracing method based on recognition of face according to claim 1 is characterized in that: the line in the described step 2, classify according to the direction of each line, and be divided into 45 degree lines, 90 degree lines, 135 degree lines and 180 degree lines.
3. the video tracing method based on recognition of face according to claim 1, it is characterized in that: in the described step 3 when being preset in faceform in the tracing machine and mating, the profile of sketching the contours of when line is when being preset in faceform in the tracing machine and having 80% to be complementary, then identification is people's face, continue next step operation, the profile of sketching the contours of when line be preset in faceform in the tracing machine and do not reach 80% when being complementary, then being identified as it is not people's face, returns and proceeds people's face searching and detecting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013102523837A CN103336948A (en) | 2013-06-24 | 2013-06-24 | Video tracking method based on face recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013102523837A CN103336948A (en) | 2013-06-24 | 2013-06-24 | Video tracking method based on face recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103336948A true CN103336948A (en) | 2013-10-02 |
Family
ID=49245105
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013102523837A Pending CN103336948A (en) | 2013-06-24 | 2013-06-24 | Video tracking method based on face recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103336948A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103916615A (en) * | 2014-04-03 | 2014-07-09 | 山大鲁能信息科技有限公司 | Recording and broadcasting system with automatic recognition function and working method thereof |
CN103957396A (en) * | 2014-05-14 | 2014-07-30 | 姚杰 | Image processing method and device used when tongue diagnosis is conducted with intelligent device and equipment |
CN104065924A (en) * | 2014-06-23 | 2014-09-24 | 苏州阔地网络科技有限公司 | On-line synchronization classroom intelligent tracking method and system |
CN105578044A (en) * | 2015-12-22 | 2016-05-11 | 杭州凡龙科技有限公司 | Panoramic view adaptive teacher image analysis method |
CN107403437A (en) * | 2016-05-19 | 2017-11-28 | 上海慧流云计算科技有限公司 | The method, apparatus and robot of robotic tracking's object |
CN108171789A (en) * | 2017-12-21 | 2018-06-15 | 迈吉客科技(北京)有限公司 | A kind of virtual image generation method and system |
CN109670451A (en) * | 2018-12-20 | 2019-04-23 | 天津天地伟业信息系统集成有限公司 | Automatic face recognition tracking |
CN110738173A (en) * | 2019-10-15 | 2020-01-31 | 安徽江淮汽车集团股份有限公司 | Face recognition system and method |
CN111614899A (en) * | 2020-05-15 | 2020-09-01 | 高斯贝尔数码科技股份有限公司 | Customized video content generation method and system based on face recognition |
WO2021036223A1 (en) * | 2019-08-29 | 2021-03-04 | 五邑大学 | Education assistant robot and control method therefor |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101916370A (en) * | 2010-08-31 | 2010-12-15 | 上海交通大学 | Method for processing non-feature regional images in face detection |
CN102096802A (en) * | 2009-12-11 | 2011-06-15 | 华为技术有限公司 | Face detection method and device |
CN102812474A (en) * | 2009-12-28 | 2012-12-05 | 索夫特基奈蒂克软件公司 | Head Recognition Method |
-
2013
- 2013-06-24 CN CN2013102523837A patent/CN103336948A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096802A (en) * | 2009-12-11 | 2011-06-15 | 华为技术有限公司 | Face detection method and device |
CN102812474A (en) * | 2009-12-28 | 2012-12-05 | 索夫特基奈蒂克软件公司 | Head Recognition Method |
CN101916370A (en) * | 2010-08-31 | 2010-12-15 | 上海交通大学 | Method for processing non-feature regional images in face detection |
Non-Patent Citations (3)
Title |
---|
何为 等: "一种基于肤色的复杂背景人脸检测方法", 《电子技术应用》 * |
向元平 等: "基于正面人脸图像的人脸轮廓的提取", 《微计算机信息》 * |
梁路宏 等: "人脸检测研究综述", 《计算机学报》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103916615A (en) * | 2014-04-03 | 2014-07-09 | 山大鲁能信息科技有限公司 | Recording and broadcasting system with automatic recognition function and working method thereof |
CN103957396A (en) * | 2014-05-14 | 2014-07-30 | 姚杰 | Image processing method and device used when tongue diagnosis is conducted with intelligent device and equipment |
CN104065924A (en) * | 2014-06-23 | 2014-09-24 | 苏州阔地网络科技有限公司 | On-line synchronization classroom intelligent tracking method and system |
CN105578044A (en) * | 2015-12-22 | 2016-05-11 | 杭州凡龙科技有限公司 | Panoramic view adaptive teacher image analysis method |
CN107403437A (en) * | 2016-05-19 | 2017-11-28 | 上海慧流云计算科技有限公司 | The method, apparatus and robot of robotic tracking's object |
CN108171789A (en) * | 2017-12-21 | 2018-06-15 | 迈吉客科技(北京)有限公司 | A kind of virtual image generation method and system |
CN108171789B (en) * | 2017-12-21 | 2022-01-18 | 迈吉客科技(北京)有限公司 | Virtual image generation method and system |
CN109670451A (en) * | 2018-12-20 | 2019-04-23 | 天津天地伟业信息系统集成有限公司 | Automatic face recognition tracking |
WO2021036223A1 (en) * | 2019-08-29 | 2021-03-04 | 五邑大学 | Education assistant robot and control method therefor |
CN110738173A (en) * | 2019-10-15 | 2020-01-31 | 安徽江淮汽车集团股份有限公司 | Face recognition system and method |
CN111614899A (en) * | 2020-05-15 | 2020-09-01 | 高斯贝尔数码科技股份有限公司 | Customized video content generation method and system based on face recognition |
CN111614899B (en) * | 2020-05-15 | 2021-11-23 | 高斯贝尔数码科技股份有限公司 | Customized video content generation method and system based on face recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103336948A (en) | Video tracking method based on face recognition | |
CN103295016B (en) | Behavior recognition method based on depth and RGB information and multi-scale and multidirectional rank and level characteristics | |
Chen et al. | A deep learning approach to drone monitoring | |
Zhang et al. | Real-time multiple human perception with color-depth cameras on a mobile robot | |
CN103871079B (en) | Wireless vehicle tracking based on machine learning and light stream | |
CN102081918B (en) | Video image display control method and video image display device | |
Voit et al. | Neural network-based head pose estimation and multi-view fusion | |
Yang et al. | Robust eyelid tracking for fatigue detection | |
CN107862240B (en) | Multi-camera collaborative face tracking method | |
CN105741324A (en) | Moving object detection identification and tracking method on moving platform | |
CN103902985B (en) | High-robustness real-time lane detection algorithm based on ROI | |
CN108197534A (en) | A kind of head part's attitude detecting method, electronic equipment and storage medium | |
CN104794439A (en) | Real-time approximate frontal face image optimizing method and system based on several cameras | |
CN105138990A (en) | Single-camera-based gesture convex hull detection and palm positioning method | |
CN105931276B (en) | A kind of long-time face tracking method based on patrol robot intelligence cloud platform | |
CN107230267A (en) | Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method | |
CN103995595A (en) | Game somatosensory control method based on hand gestures | |
CN107808376A (en) | A kind of detection method of raising one's hand based on deep learning | |
CN104484672B (en) | Quick licence plate recognition method based on multiframe picture and autonomous learning | |
CN106920247A (en) | A kind of method for tracking target and device based on comparison network | |
CN105976401A (en) | Target tracking method and system based on partitioned multi-example learning algorithm | |
CN106022211B (en) | A method of utilizing gesture control multimedia equipment | |
CN103544478A (en) | All-dimensional face detection method and system | |
CN102184016A (en) | Noncontact type mouse control method based on video sequence recognition | |
CN109712171A (en) | A kind of Target Tracking System and method for tracking target based on correlation filter |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131002 |
|
RJ01 | Rejection of invention patent application after publication |