CN101794385A - Multi-angle multi-target fast human face tracking method used in video sequence - Google Patents
Multi-angle multi-target fast human face tracking method used in video sequence Download PDFInfo
- Publication number
- CN101794385A CN101794385A CN 201010129492 CN201010129492A CN101794385A CN 101794385 A CN101794385 A CN 101794385A CN 201010129492 CN201010129492 CN 201010129492 CN 201010129492 A CN201010129492 A CN 201010129492A CN 101794385 A CN101794385 A CN 101794385A
- Authority
- CN
- China
- Prior art keywords
- face
- people
- human face
- skin
- target
- 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.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a multi-angle multi-target fast human face tracking method used in a video sequence, which belongs to the technical field of video processing. Through multi-angle human face fast detection and color histogram establishment in a human face region, a color probability graph of an image to be detected is calculated, Camshift arithmetic iterating results are used for updating the human face region position and simultaneously upgrading a human face moving model established by a Kalman filter, and at the same time, the human face prediction is carried out when a target is shielded: when the human face is shielded, the human region position is predicted by the Kalman filter, and then, the human face moving model is updated. The invention can fast eliminate the non-human face region so that the real-time multi-angle multi human face target tacking becomes possible. At the same time, through the introduction of the Kalman filter, the invention can use the prediction results of the Kalman filter for updating the position of the shielded target when the target shielding occurs in the video sequence, and the tracking difficulty caused by shielding can be perfectly overcome.
Description
Technical field
What the present invention relates to is a kind of method of technical field of video processing, specifically is a kind of multi-angle multi-target fast human face tracking method that is used for video sequence.
Background technology
People's face in the video sequence detects with tracking technique and is with a wide range of applications, at national security, military security and public safety field, intelligent entrance guard, intelligent video monitoring, public security are deployed to ensure effective monitoring and control of illegal activities, customs's authentication, the checking of driver's driving license etc. all are widely used.
Find through retrieval prior art, AdaBoost method for detecting human face based on cascade structure, be considered to effective people's face detection scheme at present, as Chinese patent literature CN101350062A, open day 2009-1-21, put down in writing a kind of " based on the fast face detecting method of video ", this technology utilizes the time-space domain feature between frame of video to carry out people's face detection of foreground area by pre-service, and people's face testing process is divided into two kinds of different patterns of examination pattern and tracing mode.To break away from guarded region if can't detect people's face in the estimation range in the tracing mode or predict people's face of following the tracks of in next frame, testing process changes the examination pattern over to, and foreground area is done comprehensive search, again people's face information in collection monitoring zone.The front face sorter that this scheme utilization trains carries out people's face to the prospect estimation range and detects, to reach the purpose that improves detection speed.But, for a plurality of angle people's face targets in the video sequence, only rely on AdaBoost to detect and the prospect Forecasting Methodology, by the people face sorter of each frame in the video with different angles detected, be difficult to reach the requirement of video tracking real-time.
Summary of the invention
The present invention is directed to the prior art above shortcomings, a kind of multi-angle multi-target fast human face tracking method that is used for video sequence is provided, can get rid of non-face zone fast, make the real-time multi-angle plurality of human faces target following of video sequence become possibility; Simultaneously,, when in video sequence, target occlusion occurring, utilize predicting the outcome of Kalman filter, upgrade the position of the target that is blocked, can overcome the tracking difficulty of bringing by blocking preferably by introducing Kalman filter.
The present invention is achieved by the following technical solutions, the present invention includes step:
The first step, multi-angle people's face fast detecting: the frame to be detected in the video sequence is carried out skin color segmentation, with people's face sorter of different angles area of skin color is carried out people's face and detect, and merge people's face testing result.
Described skin color segmentation is meant: utilize features of skin colors, frame to be detected is transformed into the hsv color space by the RGB color space, then according to the face complexion model, extract area of skin color and reject non-area of skin color.
Described features of skin colors is meant: the color of human body skin is human body surface one of notable attribute the most with respect to other objects, can utilize this feature of the colour of skin that human body and other objects are made a distinction.
Described face complexion model is meant: utilize the colour of skin under common illumination condition, can be collected at the characteristic in certain specific zone in the color space, by colour of skin image sampling being set up a distribution function or being sought the appropriate threshold that the colour of skin distributes, just area of skin color can be extracted from background image.
Described people's face detects and is meant: utilize the colour of skin area in the integrogram calculated candidate zone earlier, when colour of skin area less than preset threshold, the zone of then getting rid of this colour of skin area correspondence, otherwise the people's face sorter that utilizes the training of AdaBoost algorithm to obtain detects the candidate region, if testing result is true, then the candidate region is a human face region; Otherwise the candidate region is non-face zone.
Described colour of skin area is S
Skin=ii
A+ ii
D-(ii
B+ ii
C), wherein: S
SkinColour of skin area in the expression rectangular area ABCD, span are the height of width * rectangle ABCD of 0 to 255 * rectangle ABCD, ii
tFor at an integrogram at t place, span is 0 to 255 * picture traverse to be detected * picture altitude to be detected.
Second the step, do not occur overlapping when two people's face target areas, then each is set up H passage color histogram and calculate H passage color histogram human face region, calculate people's face target location with the Camshift iterative algorithm then, upgrade Kalman filter people face target movement model, otherwise carried out for the 3rd step;
Described calculating H passage color histogram, be meant: the color probability graph that calculates image to be detected by H passage color histogram, with the height of colour brightness as judging the centroid position criterion, in the color probability graph, calculate the centroid position of region of search with the Camshift iterative algorithm, dynamically adjust the target window size, and people's face motion model of Kalman filter foundation.
Face tracking when the 3rd step, target occlusion: overlapping if any two people's face targets occur, by the position that Kalman filter is predicted the people's face that is blocked, the Kalman filter parameter is upgraded in the people's face position that utilizes the Kalman to predict simultaneously.
Compared with prior art, the speed that the present invention can significantly improve detection, follow the tracks of, the real-time follow-up of realization multi-angle, plurality of human faces, the video to 480 * 320, the per second tracking velocity can reach more than 35 frames.Follow the tracks of for the multi-angle in the general scene, plurality of human faces, accuracy rate can reach more than 95%.
Description of drawings
Fig. 1 is a process flow diagram of the present invention.
Fig. 2 is a legend to be measured;
Wherein: a detects legend to front face; B detects legend to left widow's face; C detects legend to right widow's face; D detects the legend after merging to positive, side people's face.
Fig. 3 is for handling the back legend;
Wherein: a is through the legend after the skin color segmentation; B is the color probability graph.
Fig. 4 is an embodiment part tracking results synoptic diagram.
Embodiment
Below embodiments of the invention are elaborated, present embodiment is being to implement under the prerequisite with the technical solution of the present invention, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
As shown in Figure 1, present embodiment comprises the steps:
The first step, multi-angle people's face fast detecting: frame to be detected is carried out skin color segmentation, utilize integrogram to reject non-area of skin color fast, area of skin color is carried out people's face detect, the people's face sorter detected image with different angles merges last people's face surveyed area.
Second step, the face tracking when target occlusion not occurring: human face region is set up color histogram, calculate the color probability graph of image to be detected, with the iteration result of Camshift algorithm, upgrade the human face region position, upgrade people's face motion model of setting up by Kalman filter simultaneously.
The 3rd step, the prediction of the people's face during target occlusion: if people's face blocks, by Kalman filter prediction human face region position, new person's face motion model more again.
Above-mentioned multi-angle people's face fast detecting step is as follows:
Utilize features of skin colors, image is transformed into the hsv color space by the RGB color space, overcome the RGB color space illumination brightness is changed relatively more responsive defective, according to the face complexion model, extract area of skin color, shown in Fig. 3 a.Before with multi-angle human-face detector detected image, the colour of skin area in the first calculated candidate zone is if colour of skin area less than preset threshold, is then got rid of this zone, to improve the speed that detects at once; Otherwise the people's face sorter that utilizes the training of AdaBoost algorithm to obtain detects the candidate region, if testing result is true, then the candidate region is a human face region; Otherwise the candidate region is non-face zone.
And the colour of skin area of candidate region can directly be tried to achieve S by integrogram
Skin=ii
A+ ii
D-(ii
B+ ii
C), shown in Fig. 3 a, wherein: S
SkinColour of skin area in the expression rectangular area ABCD, span is [height of the width of 0,255 * rectangle ABCD * rectangle ABCD], ii
tFor at an integrogram at t place, span is [0, a 255 * picture traverse to be detected * picture altitude to be detected].
Merge all angles human-face detector at last and detect the human face region obtain, testing result as shown in Figure 2, a among Fig. 2, b, c and d represent front, left side, people from right side face respectively and merge people's face testing result of all angles at last.
Above-mentioned face tracking method specific implementation method when target occlusion not occurring is as follows:
Judge the relative position between people's face target area, if any two human face regions do not occur overlapping, the H passage color histogram of each human face region that calculating is obtained by step 1), by H passage color histogram, calculate the color probability graph of image to be detected, shown in Fig. 3 b, brightness is high more more near people's face color, use the Camshift iterative algorithm, in the color probability graph, calculate the centroid position of region of search, dynamically adjust the target window size, upgrade the human face region position, upgrade people's face motion model of setting up by Kalman filter simultaneously.
People's face prediction implementation method during above-mentioned target occlusion is as follows:
Judge the relative position between people's face target area, if any two human face regions occur overlapping, by the human face region position that the prediction of Kalman filter people face motion model is blocked, Kalman filter people face motion model parameters is upgraded in the human face region position that utilizes the Kalman to predict simultaneously.Forecasting process is promptly shown in the dotted line among Fig. 1.Predict the outcome as Fig. 4 the 3rd and the 20th frame, when two human face regions occur when overlapping, predict (shown in the white rectangle frame) by Kalman filter people face motion model, even when people's face was blocked fully, Kalman filter people's face motion model still can predict the position of people's face.
Claims (6)
1. a multi-angle multi-target fast human face tracking method that is used for video sequence is characterized in that, may further comprise the steps:
The first step, multi-angle people's face fast detecting: the frame to be detected in the video sequence is carried out skin color segmentation, with people's face sorter of different angles area of skin color is carried out people's face and detect, and merge people's face testing result;
Second the step, do not occur overlapping when two people's face target areas, then each is set up H passage color histogram and calculate H passage color histogram human face region, calculate people's face target location with the Camshift iterative algorithm then, upgrade Kalman filter people face target movement model, otherwise carried out for the 3rd step;
Face tracking when the 3rd step, target occlusion: overlapping if any two people's face targets occur, by the position that Kalman filter is predicted the people's face that is blocked, the Kalman filter parameter is upgraded in the people's face position that utilizes the Kalman to predict simultaneously.
2. the multi-angle multi-target fast human face tracking method that is used for video sequence according to claim 1, it is characterized in that, described skin color segmentation is meant: utilize features of skin colors, frame to be detected is transformed into the hsv color space by the RGB color space, according to the face complexion model, extract area of skin color and reject non-area of skin color then.
3. the multi-angle multi-target fast human face tracking method that is used for video sequence according to claim 2, it is characterized in that, described face complexion model is meant: by colour of skin image sampling being set up a distribution function or being sought the appropriate threshold that the colour of skin distributes, area of skin color is extracted from background image.
4. the multi-angle multi-target fast human face tracking method that is used for video sequence according to claim 1, it is characterized in that, described people's face detects and is meant: utilize the colour of skin area in the integrogram calculated candidate zone earlier, when colour of skin area less than preset threshold, the zone of then getting rid of this colour of skin area correspondence, otherwise the people's face sorter that utilizes the training of AdaBoost algorithm to obtain detects the candidate region, if testing result is true, then the candidate region is a human face region; Otherwise the candidate region is non-face zone.
5. the multi-angle multi-target fast human face tracking method that is used for video sequence according to claim 1 is characterized in that, described colour of skin area is S
Skin=ii
A+ ii
D-(ii
B+ ii
C), wherein: S
SkinColour of skin area in the expression rectangular area ABCD, span are the height of width * rectangle ABCD of 0 to 255 * rectangle ABCD, ii
tFor at an integrogram at t place, span is 0 to 255 * picture traverse to be detected * picture altitude to be detected.
6. the multi-angle multi-target fast human face tracking method that is used for video sequence according to claim 1, it is characterized in that, described calculating H passage color histogram, be meant: the color probability graph that calculates image to be detected by H passage color histogram, with the height of colour brightness as judging the centroid position criterion, in the color probability graph, calculate the centroid position of region of search with the Camshift iterative algorithm, dynamically adjust the target window size, and people's face motion model of Kalman filter foundation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010101294926A CN101794385B (en) | 2010-03-23 | 2010-03-23 | Multi-angle multi-target fast human face tracking method used in video sequence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010101294926A CN101794385B (en) | 2010-03-23 | 2010-03-23 | Multi-angle multi-target fast human face tracking method used in video sequence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101794385A true CN101794385A (en) | 2010-08-04 |
CN101794385B CN101794385B (en) | 2012-11-21 |
Family
ID=42587067
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010101294926A Expired - Fee Related CN101794385B (en) | 2010-03-23 | 2010-03-23 | Multi-angle multi-target fast human face tracking method used in video sequence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101794385B (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102496009A (en) * | 2011-12-09 | 2012-06-13 | 北京汉邦高科数字技术股份有限公司 | Multi-face tracking method for intelligent bank video monitoring |
CN102542244A (en) * | 2010-12-15 | 2012-07-04 | 财团法人工业技术研究院 | Face detection method and system and computer program product |
CN102622604A (en) * | 2012-02-14 | 2012-08-01 | 西安电子科技大学 | Multi-angle human face detecting method based on weighting of deformable components |
CN102855496A (en) * | 2012-08-24 | 2013-01-02 | 苏州大学 | Method and system for authenticating shielded face |
CN103116763A (en) * | 2013-01-30 | 2013-05-22 | 宁波大学 | Vivo-face detection method based on HSV (hue, saturation, value) color space statistical characteristics |
CN103632126A (en) * | 2012-08-20 | 2014-03-12 | 华为技术有限公司 | Human face tracking method and device |
CN103700112A (en) * | 2012-09-27 | 2014-04-02 | 中国航天科工集团第二研究院二O七所 | Sheltered target tracking method based on mixed predicting strategy |
CN104281837A (en) * | 2014-09-26 | 2015-01-14 | 哈尔滨工业大学深圳研究生院 | Pedestrian tracking method combining Kalman filtering with ROI expansion between adjacent frames |
CN104318211A (en) * | 2014-10-17 | 2015-01-28 | 中国传媒大学 | Anti-shielding face tracking method |
CN104573614A (en) * | 2013-10-22 | 2015-04-29 | 北京三星通信技术研究有限公司 | Equipment and method for tracking face |
CN105069431A (en) * | 2015-08-07 | 2015-11-18 | 成都明图通科技有限公司 | Method and device for positioning human face |
CN105427346A (en) * | 2015-12-01 | 2016-03-23 | 中国农业大学 | Motion target tracking method and system |
CN105868574A (en) * | 2016-04-25 | 2016-08-17 | 南京大学 | Human face tracking optimization method for camera and intelligent health monitoring system based on videos |
CN106022220A (en) * | 2016-05-09 | 2016-10-12 | 西安北升信息科技有限公司 | Method for performing multi-face tracking on participating athletes in sports video |
CN106650675A (en) * | 2016-12-28 | 2017-05-10 | 天津天地伟业生产力促进有限公司 | Embedded system-based real-time face detection algorithm |
CN106780542A (en) * | 2016-12-29 | 2017-05-31 | 北京理工大学 | A kind of machine fish tracking of the Camshift based on embedded Kalman filter |
CN107122762A (en) * | 2017-05-16 | 2017-09-01 | 甘肃政法学院 | A kind of processing method for compound movement image |
CN107680123A (en) * | 2017-08-30 | 2018-02-09 | 王连圭 | Trans-regional people's volumetric video single goal intelligent-tracking algorithm device |
CN107995418A (en) * | 2017-11-21 | 2018-05-04 | 维沃移动通信有限公司 | A kind of image pickup method, device and mobile terminal |
CN108280524A (en) * | 2017-01-05 | 2018-07-13 | 通用汽车环球科技运作有限责任公司 | The system and method for identifying vehicle and generating reservation information |
CN108734091A (en) * | 2018-03-30 | 2018-11-02 | 暨南大学 | Compartment anomaly detection method, computer installation and computer readable storage medium |
CN109348190A (en) * | 2018-12-05 | 2019-02-15 | 吉林大学 | Monitoring system and method is fallen down based on video monitoring |
CN109345566A (en) * | 2018-09-28 | 2019-02-15 | 上海应用技术大学 | Motion target tracking method and system |
CN109614841A (en) * | 2018-04-26 | 2019-04-12 | 杭州智诺科技股份有限公司 | Fast face detecting method in embedded system |
CN110706253A (en) * | 2019-09-19 | 2020-01-17 | 中国科学院自动化研究所 | Target tracking method, system and device based on apparent feature and depth feature |
CN111582212A (en) * | 2020-05-15 | 2020-08-25 | 山东大学 | Multi-domain fusion micro-expression detection method based on motion unit |
CN113876311A (en) * | 2021-09-02 | 2022-01-04 | 天津大学 | Self-adaptively-selected non-contact multi-player heart rate efficient extraction device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1924894A (en) * | 2006-09-27 | 2007-03-07 | 北京中星微电子有限公司 | Multiple attitude human face detection and track system and method |
CN101231703A (en) * | 2008-02-28 | 2008-07-30 | 上海交通大学 | Method for tracing a plurality of human faces base on correlate vector machine to improve learning |
CN101620673A (en) * | 2009-06-18 | 2010-01-06 | 北京航空航天大学 | Robust face detecting and tracking method |
-
2010
- 2010-03-23 CN CN2010101294926A patent/CN101794385B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1924894A (en) * | 2006-09-27 | 2007-03-07 | 北京中星微电子有限公司 | Multiple attitude human face detection and track system and method |
CN101231703A (en) * | 2008-02-28 | 2008-07-30 | 上海交通大学 | Method for tracing a plurality of human faces base on correlate vector machine to improve learning |
CN101620673A (en) * | 2009-06-18 | 2010-01-06 | 北京航空航天大学 | Robust face detecting and tracking method |
Non-Patent Citations (3)
Title |
---|
《北京理工大学学报》 20000831 刘万春 等 基于肤色的人脸实时跟踪方法 第20卷, 第4期 2 * |
《微计算机应用》 20080229 王亮亮 等 基于人脸检测和CAMSHIFT算法的人脸跟踪*** 第29卷, 第2期 2 * |
《计算机应用研究》 20080731 *** 等 基于mean_shift算法的人脸实时跟踪方法 第25卷, 第7期 2 * |
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102542244A (en) * | 2010-12-15 | 2012-07-04 | 财团法人工业技术研究院 | Face detection method and system and computer program product |
US8559707B2 (en) | 2010-12-15 | 2013-10-15 | Industrial Technology Research Institute | System and method for face detection using face region location and size predictions and computer program product thereof |
CN102496009A (en) * | 2011-12-09 | 2012-06-13 | 北京汉邦高科数字技术股份有限公司 | Multi-face tracking method for intelligent bank video monitoring |
CN102496009B (en) * | 2011-12-09 | 2013-09-18 | 北京汉邦高科数字技术股份有限公司 | Multi-face tracking method for intelligent bank video monitoring |
CN102622604A (en) * | 2012-02-14 | 2012-08-01 | 西安电子科技大学 | Multi-angle human face detecting method based on weighting of deformable components |
CN102622604B (en) * | 2012-02-14 | 2014-01-15 | 西安电子科技大学 | Multi-angle human face detecting method based on weighting of deformable components |
CN103632126A (en) * | 2012-08-20 | 2014-03-12 | 华为技术有限公司 | Human face tracking method and device |
CN102855496A (en) * | 2012-08-24 | 2013-01-02 | 苏州大学 | Method and system for authenticating shielded face |
CN102855496B (en) * | 2012-08-24 | 2016-05-25 | 苏州大学 | Block face authentication method and system |
CN103700112A (en) * | 2012-09-27 | 2014-04-02 | 中国航天科工集团第二研究院二O七所 | Sheltered target tracking method based on mixed predicting strategy |
CN103116763A (en) * | 2013-01-30 | 2013-05-22 | 宁波大学 | Vivo-face detection method based on HSV (hue, saturation, value) color space statistical characteristics |
CN103116763B (en) * | 2013-01-30 | 2016-01-20 | 宁波大学 | A kind of living body faces detection method based on hsv color Spatial Statistical Character |
CN104573614A (en) * | 2013-10-22 | 2015-04-29 | 北京三星通信技术研究有限公司 | Equipment and method for tracking face |
CN104573614B (en) * | 2013-10-22 | 2020-01-03 | 北京三星通信技术研究有限公司 | Apparatus and method for tracking human face |
CN104281837A (en) * | 2014-09-26 | 2015-01-14 | 哈尔滨工业大学深圳研究生院 | Pedestrian tracking method combining Kalman filtering with ROI expansion between adjacent frames |
CN104281837B (en) * | 2014-09-26 | 2018-05-25 | 哈尔滨工业大学深圳研究生院 | With reference to Kalman filtering and the adjacent widened pedestrian tracting methods of interframe ROI |
CN104318211A (en) * | 2014-10-17 | 2015-01-28 | 中国传媒大学 | Anti-shielding face tracking method |
CN105069431B (en) * | 2015-08-07 | 2018-09-14 | 成都明图通科技有限公司 | The localization method and device of face |
CN105069431A (en) * | 2015-08-07 | 2015-11-18 | 成都明图通科技有限公司 | Method and device for positioning human face |
CN105427346A (en) * | 2015-12-01 | 2016-03-23 | 中国农业大学 | Motion target tracking method and system |
CN105427346B (en) * | 2015-12-01 | 2018-06-29 | 中国农业大学 | A kind of motion target tracking method and system |
CN105868574A (en) * | 2016-04-25 | 2016-08-17 | 南京大学 | Human face tracking optimization method for camera and intelligent health monitoring system based on videos |
CN105868574B (en) * | 2016-04-25 | 2018-12-14 | 南京大学 | A kind of optimization method of camera track human faces and wisdom health monitor system based on video |
CN106022220A (en) * | 2016-05-09 | 2016-10-12 | 西安北升信息科技有限公司 | Method for performing multi-face tracking on participating athletes in sports video |
CN106022220B (en) * | 2016-05-09 | 2020-02-28 | 北京河马能量体育科技有限公司 | Method for tracking multiple faces of participating athletes in sports video |
CN106650675A (en) * | 2016-12-28 | 2017-05-10 | 天津天地伟业生产力促进有限公司 | Embedded system-based real-time face detection algorithm |
CN106650675B (en) * | 2016-12-28 | 2020-01-21 | 天地伟业技术有限公司 | Real-time face detection method based on embedded system |
CN106780542A (en) * | 2016-12-29 | 2017-05-31 | 北京理工大学 | A kind of machine fish tracking of the Camshift based on embedded Kalman filter |
CN108280524B (en) * | 2017-01-05 | 2021-11-02 | 通用汽车环球科技运作有限责任公司 | System and method for identifying vehicles and generating reservation information |
CN108280524A (en) * | 2017-01-05 | 2018-07-13 | 通用汽车环球科技运作有限责任公司 | The system and method for identifying vehicle and generating reservation information |
CN107122762A (en) * | 2017-05-16 | 2017-09-01 | 甘肃政法学院 | A kind of processing method for compound movement image |
CN107680123A (en) * | 2017-08-30 | 2018-02-09 | 王连圭 | Trans-regional people's volumetric video single goal intelligent-tracking algorithm device |
CN107995418A (en) * | 2017-11-21 | 2018-05-04 | 维沃移动通信有限公司 | A kind of image pickup method, device and mobile terminal |
CN107995418B (en) * | 2017-11-21 | 2020-07-21 | 维沃移动通信有限公司 | Shooting method and device and mobile terminal |
CN108734091A (en) * | 2018-03-30 | 2018-11-02 | 暨南大学 | Compartment anomaly detection method, computer installation and computer readable storage medium |
CN109614841A (en) * | 2018-04-26 | 2019-04-12 | 杭州智诺科技股份有限公司 | Fast face detecting method in embedded system |
CN109614841B (en) * | 2018-04-26 | 2023-04-18 | 杭州智诺科技股份有限公司 | Rapid face detection method in embedded system |
CN109345566A (en) * | 2018-09-28 | 2019-02-15 | 上海应用技术大学 | Motion target tracking method and system |
CN109348190A (en) * | 2018-12-05 | 2019-02-15 | 吉林大学 | Monitoring system and method is fallen down based on video monitoring |
CN110706253A (en) * | 2019-09-19 | 2020-01-17 | 中国科学院自动化研究所 | Target tracking method, system and device based on apparent feature and depth feature |
CN110706253B (en) * | 2019-09-19 | 2022-03-08 | 中国科学院自动化研究所 | Target tracking method, system and device based on apparent feature and depth feature |
CN111582212A (en) * | 2020-05-15 | 2020-08-25 | 山东大学 | Multi-domain fusion micro-expression detection method based on motion unit |
CN111582212B (en) * | 2020-05-15 | 2023-04-18 | 山东大学 | Multi-domain fusion micro-expression detection method based on motion unit |
CN113876311A (en) * | 2021-09-02 | 2022-01-04 | 天津大学 | Self-adaptively-selected non-contact multi-player heart rate efficient extraction device |
CN113876311B (en) * | 2021-09-02 | 2023-09-15 | 天津大学 | Non-contact type multi-player heart rate efficient extraction device capable of adaptively selecting |
Also Published As
Publication number | Publication date |
---|---|
CN101794385B (en) | 2012-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101794385B (en) | Multi-angle multi-target fast human face tracking method used in video sequence | |
CN101739686B (en) | Moving object tracking method and system thereof | |
O’Malley et al. | Detection of pedestrians in far-infrared automotive night vision using region-growing and clothing distortion compensation | |
Cucchiara et al. | Improving shadow suppression in moving object detection with HSV color information | |
Hsieh et al. | Shadow elimination for effective moving object detection by Gaussian shadow modeling | |
US7787656B2 (en) | Method for counting people passing through a gate | |
CN113011367B (en) | Abnormal behavior analysis method based on target track | |
Xu et al. | A people counting system based on head-shoulder detection and tracking in surveillance video | |
CA3094424C (en) | Safety monitoring and early-warning method for man-machine interaction behavior of underground conveyor belt operator | |
Pan et al. | Robust abandoned object detection using region-level analysis | |
CN108596129A (en) | A kind of vehicle based on intelligent video analysis technology gets over line detecting method | |
Li et al. | Abandoned objects detection using double illumination invariant foreground masks | |
CN104616006B (en) | A kind of beard method for detecting human face towards monitor video | |
CN106920253A (en) | It is a kind of based on the multi-object tracking method for blocking layering | |
CN105554462A (en) | Remnant detection method | |
CN104331687B (en) | A kind of behavioral value method of not fastening the safety belt based on vehicular video analysis | |
CN103793715A (en) | Underground worker target tracing method based on scene information mining | |
CN104281837A (en) | Pedestrian tracking method combining Kalman filtering with ROI expansion between adjacent frames | |
CN104200199A (en) | TOF (Time of Flight) camera based bad driving behavior detection method | |
CN103049788A (en) | Computer-vision-based system and method for detecting number of pedestrians waiting to cross crosswalk | |
CN103577832A (en) | People flow statistical method based on spatio-temporal context | |
CN106951820B (en) | Passenger flow statistical method based on annular template and ellipse fitting | |
Xia et al. | Automatic multi-vehicle tracking using video cameras: An improved CAMShift approach | |
CN102810206A (en) | Real-time loitering detection method based on dynamic programming | |
CN101848369A (en) | Method for detecting video stop event based on self-adapting double-background model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121121 Termination date: 20150323 |
|
EXPY | Termination of patent right or utility model |