CN108304001A - A kind of Face datection tracking, ball machine head rotation control method and ball machine - Google Patents
A kind of Face datection tracking, ball machine head rotation control method and ball machine Download PDFInfo
- Publication number
- CN108304001A CN108304001A CN201810134315.3A CN201810134315A CN108304001A CN 108304001 A CN108304001 A CN 108304001A CN 201810134315 A CN201810134315 A CN 201810134315A CN 108304001 A CN108304001 A CN 108304001A
- Authority
- CN
- China
- Prior art keywords
- face
- center
- frame
- image
- ball machine
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of Face datection tracking, ball machine head rotation control method and ball machines.The face detecting and tracking method includes step:It acquires image and Face datection is carried out to described image, with the center of the face frame of each frame image of determination;The center of the face frame and image center location are adjusted, make center and the image center location overlapping of face frame, to realize to the face in the tracking box of the current frame image into line trace.The face detecting and tracking method advantageously reduces false detection rate, improves the accuracy rate of Face datection.The ball machine head rotation control method carries out Face datection using the face detecting and tracking method, is conducive to ensure the fluency in robot head rotation process, avoids occurring Caton phenomenon in rotation process.
Description
Technical field
The invention belongs to field of face identification more particularly to a kind of Face datection tracking, the controls of ball machine head rotation
Method and ball machine.
Background technology
In the prior art, ball machine can be tracked automatically according to shooting picture background modeling or algorithm of target detection, according to mesh
Target signature tracking target.Its shortcoming is that the secondary focusing that cannot be maximized zoom with target, can not achieve target, to lead
Target face resolution ratio is caused to be too low to carry out recognition of face comparison.
Invention content
Technical problem to be solved by the invention is to provide a kind of Face datection tracking, ball machine head rotation controlling parties
Method and ball machine are shot and detection most clearly face with realizing.
The technical solution that the present invention solves above-mentioned technical problem is as follows:
A kind of Face datection tracking, includes the following steps:
A. by ball machine head rotation to area-of-interest;
B. image is acquired according to current ball machine picture and Face datection is carried out to described image, with each frame image of determination
Face frame initial position;
C. the face frame initial position obtained according to step B extrapolates the range of people's upper part of the body, and by the model of people's upper part of the body
It encloses as feature extraction learning region;
D. face frame tracking is carried out to the feature extraction learning region of step C according to KCF target tracking algorisms, and according to step
Face frame initial position in rapid B calculates the center of face frame:
E. image center location is calculated according to acquisition resolution, and calculates center and the picture centre position of face frame
The difference set:
F. carry out the horizontal and vertical rotation distance of control ball chain-drive section using the difference of step E as PID errors, make face frame
Center and image center location overlapping, if difference is not zero, return to step B continues next frame processing;If difference
It is zero, then carries out step G;
G. when difference is zero and stablizes at least two frame, the control ball machine zoom target that furthers makes face resolution ratio reach default
Value, to carry out Face detection and tracking.
The beneficial effects of the invention are as follows:Based on KCF target tracking algorisms into line trace, at the same by PID adjusting methods into
Mobile state adjusts the head rotation of ball machine, so that the center of face frame and image center location overlapping, after image stabilization
It is detected and captures again, realize shooting and detection most clearly face.
Based on the above technical solution, the present invention can also be improved as follows.
Further, the detailed process of the step D is:
Face frame initial position in step B is rect (x, y, w, h),
The center for calculating face frame is (x1,y1):
x1=x+w/2, y1=y+h/2;
Wherein, it in the width that the starting point of x coordinate, w are face frame, y is starting of the face frame in y-coordinate that x, which is face frame,
Point, h are respectively the height of face frame.
Further, the step E detailed processes are:
Image center location is (xc,yc):
xc=Wsrc/2, yc=Hsrc/2;
Difference is:
ex=xc-x1,ey=yc-y1;
Wherein, (Wsrc, Hsrc) is acquisition resolution, exFor face frame center and image center location in x-axis
On difference, eyFor the difference of the center of face frame and image center location on the y axis.
Further, the step F detailed processes are:
By ex、eyValue substitutes into PID formula:
Wherein, Ux(t)、Uy(t) it is respectively that ball machine is controlled in x-axis, the direction of y-axis and speed, KpFor proportionality coefficient, KiFor
Integration time constant, KdFor derivative constant, t is time variable, exi、eyiRespectively exAnd eyHistory coordinate, T be sampling when
Between.
The present invention also provides a kind of ball machine head rotation control methods, include the following steps:
The center of the face frame of current frame image is determined according to Face datection tracking above-mentioned;
Image center location is determined according to acquisition resolution;
Control ball chain-drive section rotates, so that the center of the face frame of the current frame image is moved in described image
On heart position.
The beneficial effects of the invention are as follows:Image center location is determined according to acquisition resolution, and is tracked using Face datection
Method determines the center of the face frame of current frame image, and control robot head rotation is so that tracking box is moved to center
On domain.The ball machine head rotation control method can be according to the face frame of current frame image center and image center location,
Control ball chain-drive section left-right rotation rotates upwardly and downwardly so that ball machine is more vivid during exercise.It is tracked using Face datection
Method determines the center of the face frame of current frame image, is conducive to the fluency for ensureing control ball chain-drive section rotation process,
Rotation process is avoided Caton phenomenon occur.
Further, the control ball chain-drive section rotation, so that the center movement of the face frame of the current frame image
Step on to described image center specifically includes:
Calculate horizontal-shift degree and vertical shift degree of the described image center relative to the center of face frame;
Horizontal-shift degree is rotated in the horizontal direction and is vertically rotated using PID adjusting method control ball chain-drive sections hangs down
Straight drift rate makes center and the overlapping of described image center of the face frame.
The present invention also provides a kind of ball machine, the head that ball machine is controlled using ball machine head rotation control method above-mentioned is turned
It is dynamic.
The beneficial effects of the invention are as follows:Head rotation is controlled using ball machine head rotation control method, ball machine can be made to transport
It is more vivid when dynamic.
Description of the drawings
Fig. 1 is face detecting and tracking method flow diagram of the present invention.
Specific implementation mode
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
As shown in Figure 1, a kind of Face datection tracking, includes the following steps:
A. ball machine is moved to area-of-interest;
B. image is acquired according to current ball machine picture and Face datection is carried out to described image, with each frame image of determination
Face frame initial position rect (x, y, w, h);
C. the face frame initial position obtained according to step B extrapolates the range of people's upper part of the body, and by the model of people's upper part of the body
It encloses as feature extraction learning region;
D. face frame tracking is carried out to the feature extraction learning region of step C according to KCF target tracking algorisms, and according to step
Face frame initial position in rapid B calculates the center (x of face frame1,y1):
x1=x+w/2, y1=y+h/2;
E. image center location (x is calculated according to acquisition resolution (Wsrc, Hsrc)c,yc), and calculate in face frame
The difference of heart position and image center location:
xc=Wsrc/2, yc=Hsrc/2;
ex=xc-x1,ey=yc-y1;
F. e step E obtainedx, eyAbsolute value as speed, it is positive and negative to control ball machine movement as direction, if poor
Value is not zero, then return to step B continues next frame processing;If difference is zero, step G is carried out;
By ex、eyValue substitutes into PID formula:
Wherein, Ux(t)、Uy(t) it is respectively that ball machine is controlled in x-axis, the direction of y-axis and speed, Kp is proportionality coefficient, and Ki is
Integration time constant, Kd are derivative constant, and t is time variable, exi、eyiRespectively exAnd eyHistory coordinate, T be sampling when
Between.
G. when difference is zero and stablizes at least two frame, the control ball machine zoom target that furthers makes face resolution ratio reach default
Value, to carry out Face detection and tracking.
This method is based on KCF target tracking algorisms into line trace, while carrying out dynamic regulation ball machine by PID adjusting methods
Head rotation so that the center of face frame and image center location overlapping, be detected and grab again after image stabilization
It claps, realizes shooting and detection most clearly face.
In addition, the present invention provides a kind of ball machine head rotation control method according to aforementioned Face datection tracking, packet
Include following steps:
The center of the face frame of current frame image is determined according to Face datection tracking above-mentioned;
Image center location is determined according to acquisition resolution;
Control ball chain-drive section rotates, so that the center of the face frame of the current frame image is moved in described image
On heart position, specifically include:
Calculate horizontal-shift degree and vertical shift degree of the described image center relative to the center of face frame;
Horizontal-shift degree is rotated in the horizontal direction and is vertically rotated using PID adjusting method control ball chain-drive sections hangs down
Straight drift rate makes center and the overlapping of described image center of the face frame.
The advantageous effect of this ball machine head rotation control method is:Image center location is determined according to acquisition resolution, and
Determine the center of the face frame of current frame image using Face datection tracking, control robot head rotate so that with
Track frame is moved on central area.The ball machine head rotation control method can be according to the center of the face frame of current frame image
It with image center location, control ball chain-drive section left-right rotation or rotates upwardly and downwardly so that ball machine is more vivid during exercise.It adopts
The center that the face frame of current frame image is determined with face detecting and tracking method is conducive to ensure the rotation of control ball chain-drive section
The fluency of process, avoids rotation process from Caton phenomenon occur.
The present invention also provides a kind of ball machine, the head that ball machine is controlled using ball machine head rotation control method above-mentioned is turned
It is dynamic.Head rotation is controlled using ball machine head rotation control method, ball machine can be made more vivid during exercise.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (7)
1. a kind of Face datection tracking, which is characterized in that include the following steps:
A. by ball machine head rotation to area-of-interest;
B. image is acquired according to current ball machine picture and Face datection is carried out to described image, with the face of each frame image of determination
Frame initial position;
C. the face frame initial position obtained according to step B extrapolates the range of people's upper part of the body, and the range of people's upper part of the body is made
It is characterized extraction learning region;
D. face frame tracking is carried out to the feature extraction learning region of step C according to KCF target tracking algorisms, and according to step B
In face frame initial position calculate the center of face frame:
E. image center location is calculated according to acquisition resolution, and calculates center and the image center location of face frame
Difference:
F. carry out the horizontal and vertical rotation distance of control ball chain-drive section using the difference of step E as PID errors, make the center of face frame
Position and image center location overlapping, if difference is not zero, return to step B continues next frame processing;If difference is zero,
Then enter step G;
G. when difference is zero and stablizes at least two frame, the control ball machine zoom target that furthers makes face resolution ratio reach preset value,
To carry out Face detection and tracking.
2. Face datection tracking according to claim 1, which is characterized in that the detailed process of the step D is:
Face frame initial position in step B is rect (x, y, w, h),
The center for calculating face frame is (x1,y1):
x1=x+w/2, y1=y+h/2;
Wherein, it is starting point of the face frame in y-coordinate, h that x, which is face frame in the width that the starting point of x coordinate, w are face frame, y,
The respectively height of face frame.
3. Face datection tracking according to claim 1, which is characterized in that the step E detailed processes are:
Image center location is (xc,yc):
xc=Wsrc/2, yc=Hsrc/2;
Difference is:
ex=xc-x1,ey=yc-y1;
Wherein, (Wsrc, Hsrc) is acquisition resolution, exFor the difference of the center of face frame and image center location in x-axis
Value, eyFor the difference of the center of face frame and image center location on the y axis.
4. Face datection tracking according to claim 3, which is characterized in that the step F detailed processes are:
By ex、eyValue substitutes into PID formula:
Wherein, Ux(t)、Uy(t) it is respectively that ball machine is controlled in x-axis, the direction of y-axis and speed, KpFor proportionality coefficient, KiWhen to integrate
Between constant, KdFor derivative constant, t is time variable, exi、eyiRespectively exAnd eyHistory coordinate, T is the sampling time.
5. a kind of ball machine head rotation control method, which is characterized in that include the following steps:
Face datection tracking according to any one of claim 1 to 4 determines in the face frame of current frame image
Heart position;
Image center location is determined according to acquisition resolution;
Control ball chain-drive section rotates, so that the center of the face frame of the current frame image is moved to described image centre bit
It sets.
6. ball machine head rotation control method according to claim 5, which is characterized in that the control ball chain-drive section turns
It is dynamic, so that the step that the center of the face frame of the current frame image is moved on described image center is specifically wrapped
It includes:
Calculate horizontal-shift degree and vertical shift degree of the described image center relative to the center of face frame;
Horizontal-shift degree is rotated using PID adjusting method control ball chain-drive sections in the horizontal direction and is vertically rotated vertical inclined
Shifting degree makes center and the overlapping of described image center of the face frame.
7. a kind of ball machine, which is characterized in that control ball machine using ball machine head rotation control method described in claim 5 or 6
Head rotation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810134315.3A CN108304001A (en) | 2018-02-09 | 2018-02-09 | A kind of Face datection tracking, ball machine head rotation control method and ball machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810134315.3A CN108304001A (en) | 2018-02-09 | 2018-02-09 | A kind of Face datection tracking, ball machine head rotation control method and ball machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108304001A true CN108304001A (en) | 2018-07-20 |
Family
ID=62864711
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810134315.3A Pending CN108304001A (en) | 2018-02-09 | 2018-02-09 | A kind of Face datection tracking, ball machine head rotation control method and ball machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108304001A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109618096A (en) * | 2018-12-19 | 2019-04-12 | 浙江工业大学 | A kind of automatic follower method of video record |
CN109799984A (en) * | 2019-01-15 | 2019-05-24 | 深圳前海微众银行股份有限公司 | Face frame method for drafting, device, equipment and computer readable storage medium |
CN109871760A (en) * | 2019-01-15 | 2019-06-11 | 北京奇艺世纪科技有限公司 | A kind of Face detection method, apparatus, terminal device and storage medium |
CN110046626A (en) * | 2019-04-03 | 2019-07-23 | 工极智能科技(苏州)有限公司 | Image intelligent learning dynamics tracking system and method based on PICO algorithm |
CN111757011A (en) * | 2020-07-14 | 2020-10-09 | 深圳天海宸光科技有限公司 | PID algorithm-based ball machine high-precision tracking system and method |
CN113553889A (en) * | 2020-04-26 | 2021-10-26 | 杭州萤石软件有限公司 | Face tracking method and device |
CN113642545A (en) * | 2021-10-15 | 2021-11-12 | 北京万里红科技有限公司 | Face image processing method based on multi-task learning |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102291569A (en) * | 2011-07-27 | 2011-12-21 | 上海交通大学 | Double-camera automatic coordination multi-target eagle eye observation system and observation method thereof |
US20130188070A1 (en) * | 2012-01-19 | 2013-07-25 | Electronics And Telecommunications Research Institute | Apparatus and method for acquiring face image using multiple cameras so as to identify human located at remote site |
CN103617631A (en) * | 2013-11-11 | 2014-03-05 | 山东神戎电子股份有限公司 | Tracking method based on center detection |
CN103631698A (en) * | 2013-12-20 | 2014-03-12 | 中安消技术有限公司 | Camera PTZ (pan/tilt/zoom) control method and device for target tracking |
CN104021571A (en) * | 2014-06-03 | 2014-09-03 | 浙江宇视科技有限公司 | Moving target automatic tracking method and device for improving user experience |
CN104184932A (en) * | 2013-05-20 | 2014-12-03 | 浙江大华技术股份有限公司 | Spherical camera control method and device thereof |
CN106228112A (en) * | 2016-07-08 | 2016-12-14 | 深圳市优必选科技有限公司 | Face datection tracking and robot head method for controlling rotation and robot |
US20170006215A1 (en) * | 2015-06-30 | 2017-01-05 | Canon Kabushiki Kaisha | Methods and systems for controlling a camera to perform a task |
CN106778585A (en) * | 2016-12-08 | 2017-05-31 | 腾讯科技(上海)有限公司 | A kind of face key point-tracking method and device |
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 |
-
2018
- 2018-02-09 CN CN201810134315.3A patent/CN108304001A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102291569A (en) * | 2011-07-27 | 2011-12-21 | 上海交通大学 | Double-camera automatic coordination multi-target eagle eye observation system and observation method thereof |
US20130188070A1 (en) * | 2012-01-19 | 2013-07-25 | Electronics And Telecommunications Research Institute | Apparatus and method for acquiring face image using multiple cameras so as to identify human located at remote site |
CN104184932A (en) * | 2013-05-20 | 2014-12-03 | 浙江大华技术股份有限公司 | Spherical camera control method and device thereof |
CN103617631A (en) * | 2013-11-11 | 2014-03-05 | 山东神戎电子股份有限公司 | Tracking method based on center detection |
CN103631698A (en) * | 2013-12-20 | 2014-03-12 | 中安消技术有限公司 | Camera PTZ (pan/tilt/zoom) control method and device for target tracking |
CN104021571A (en) * | 2014-06-03 | 2014-09-03 | 浙江宇视科技有限公司 | Moving target automatic tracking method and device for improving user experience |
US20170006215A1 (en) * | 2015-06-30 | 2017-01-05 | Canon Kabushiki Kaisha | Methods and systems for controlling a camera to perform a task |
CN106228112A (en) * | 2016-07-08 | 2016-12-14 | 深圳市优必选科技有限公司 | Face datection tracking and robot head method for controlling rotation and robot |
CN106778585A (en) * | 2016-12-08 | 2017-05-31 | 腾讯科技(上海)有限公司 | A kind of face key point-tracking method and device |
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 |
Non-Patent Citations (6)
Title |
---|
付伟: "PTZ行人跟踪和控制算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
叶峰 等: "共面点的摄像机肥线性畸变校正", 《光学精密工程》 * |
吕高杰 等: "电子稳像算法精度评价方法研究", 《电光与控制》 * |
汪媛媛: "宽视场主动视觉跟踪技术研究", 《中国优秀硕士论文全文数据库信息科技辑》 * |
潘振福 等: "基于视觉目标跟踪的PTZ控制方法", 《电子技术应用》 * |
赵锞锞 等: "新闻视频主持人镜头检测方法", 《新闻视频主持人镜头检测方法》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109618096A (en) * | 2018-12-19 | 2019-04-12 | 浙江工业大学 | A kind of automatic follower method of video record |
CN109799984A (en) * | 2019-01-15 | 2019-05-24 | 深圳前海微众银行股份有限公司 | Face frame method for drafting, device, equipment and computer readable storage medium |
CN109871760A (en) * | 2019-01-15 | 2019-06-11 | 北京奇艺世纪科技有限公司 | A kind of Face detection method, apparatus, terminal device and storage medium |
CN109799984B (en) * | 2019-01-15 | 2022-04-26 | 深圳前海微众银行股份有限公司 | Face frame drawing method, device and equipment and computer readable storage medium |
CN110046626A (en) * | 2019-04-03 | 2019-07-23 | 工极智能科技(苏州)有限公司 | Image intelligent learning dynamics tracking system and method based on PICO algorithm |
CN110046626B (en) * | 2019-04-03 | 2024-03-15 | 工极智能科技(苏州)有限公司 | PICO algorithm-based image intelligent learning dynamic tracking system and method |
CN113553889A (en) * | 2020-04-26 | 2021-10-26 | 杭州萤石软件有限公司 | Face tracking method and device |
CN111757011A (en) * | 2020-07-14 | 2020-10-09 | 深圳天海宸光科技有限公司 | PID algorithm-based ball machine high-precision tracking system and method |
CN113642545A (en) * | 2021-10-15 | 2021-11-12 | 北京万里红科技有限公司 | Face image processing method based on multi-task learning |
CN113642545B (en) * | 2021-10-15 | 2022-01-28 | 北京万里红科技有限公司 | Face image processing method based on multi-task learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108304001A (en) | A kind of Face datection tracking, ball machine head rotation control method and ball machine | |
CN104184932B (en) | Ball machine control method and device | |
CN107958479A (en) | A kind of mobile terminal 3D faces augmented reality implementation method | |
CN108637435A (en) | A kind of three-dimensional seam tracking system and method for view-based access control model and arc voltage sensing | |
WO2023071884A1 (en) | Gaze detection method, control method for electronic device, and related devices | |
CN103327250A (en) | Method for controlling camera lens based on pattern recognition | |
CN108513414B (en) | Stage light-following lamp system and method with self-tracking focus | |
CN107301657B (en) | A kind of video target tracking method considering target movable information | |
CN102096927A (en) | Target tracking method of independent forestry robot | |
CN105261039B (en) | A kind of self-adaptative adjustment target tracking algorism based on depth image | |
CN104469170B (en) | Binocular camera shooting device, image processing method and device | |
CN107009357A (en) | A kind of method that object is captured based on NAO robots | |
CN108672907A (en) | The online method for correcting error of arc welding robot weld seam based on structured light visual sensing | |
CN110032186A (en) | A kind of labyrinth feature identification of anthropomorphic robot and traveling method | |
CN104883524A (en) | Method and system for automatically tracking and shooting moving object in online class | |
CN103617631B (en) | A kind of tracking based on Spot detection | |
CN109366501A (en) | Gas ice hockey robot control method, device and gas ice hockey equipment | |
CN106325278B (en) | A kind of robot localization air navigation aid based on Aleuroglyphus ovatus | |
CN108989765A (en) | The tripod system of dynamically track self-timer | |
CN111932633A (en) | Method for automatically adjusting camera based on face part detection technology | |
CN108989686B (en) | Real-time shooting device based on human shape tracking and control method | |
CN110716504B (en) | Rolling ball system motion control method based on multi-closed-loop cascade control | |
Liu et al. | Improved high-speed vision system for table tennis robot | |
CN112446851A (en) | Endpoint detection algorithm based on high-speed pulse type image sensor | |
CN106530349A (en) | Dynamic positioning method and device based on ellipse center |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | 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: 20180720 |
|
RJ01 | Rejection of invention patent application after publication |