CN107396059A - A kind of panorama position adaptive student graphical analysis control method - Google Patents
A kind of panorama position adaptive student graphical analysis control method Download PDFInfo
- Publication number
- CN107396059A CN107396059A CN201710735501.8A CN201710735501A CN107396059A CN 107396059 A CN107396059 A CN 107396059A CN 201710735501 A CN201710735501 A CN 201710735501A CN 107396059 A CN107396059 A CN 107396059A
- Authority
- CN
- China
- Prior art keywords
- control
- target
- camera
- student
- close shot
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention relates to a kind of panorama position adaptive student graphical analysis control method, for classroom student's video capture.The control method, its system includes embedded host, display, one full-view camera and a close shot camera, embedded host, which is used to analyze, judges the data that camera transmits, and key frame is shown by display, two cameras shoot student's panorama and close shot in classroom respectively, it is characterized in that, embedded host is recorded in real time for the view data that camera transmits, and interference is rejected after being analyzed, if it was found that target is stood up, then camera is controlled to complete the switching action between distant view and close shot, determine whether target sits down, into next work period.The method reduces various human factors present in shooting by hand, in the case of no manual intervention, auxiliary camera is tracked shooting.
Description
Technical field
The present invention relates to a kind of panorama position adaptive student graphical analysis control method, for classroom student's video capture.
Background technology
Teaching is recorded among environment, it is necessary to which activity of the camera to student classroom is shot now, and content of shooting includes
Student's panoramic picture, student's close shot image.And traditional mode is a kind of to be shot by the way of artificial, artificial shooting is not
Only take time and effort, shooting effect tracks personal horizontal height and level differs, and can also seriously have influence on normal teaching
Flow, interference teacher teaching and student listen to the teacher；Another way is using infrared, and the technology such as ultrasonic wave carries out auxiliary shooting, this
Kind mode needs to add equipment in addition, and adds the difficulty of cost and regular maintenance.
Therefore need one kind full automatic, the technical scheme that any third party's auxiliary takes the photograph equipment is not installed, by image
Hold the various actions for analyzing student, in the case of no manual intervention, auxiliary camera is tracked shooting.
Chinese invention patent publication number " 103093654A " discloses a kind of " twin camera interactive intelligent tracing teaching system
System ", including image capture module, camera control module, user interface interaction module, thread interactive module, teacher's tracking mould
Block, student's detection module, student trace module.In teaching process, control main frame is obtained in real time by two-way image pick-up card
The shooting image of teacher and student video camera, by using the calculating of track algorithm and detection algorithm based on image processing techniques
As a result, appropriate control strategy is selected, the mutual switching between reasonable arrangement signal, and fast and flexible accurately realizes that scene is taken the photograph
Wave and the function such as pitching, scaling and focusing of camera, ensure that teacher's moment is in the appropriate location of shooting picture, realize pair
The automatic track and localization of teacher, student's panorama give the functions such as close-up shot when showing and put question to detection and writing on the blackboard, it is achieved thereby that
Anti- external interference, action are tracked without specific limitation, automated intelligent tracing teaching system of the shooting without staff on duty.The patent discloses
Technical scheme involved by hardware module it is more, relate generally to seven modules, introducing needs manually operated user interface
Interactive module and camera control module, and the technology used is also relatively complicated, it is necessary to some default numerical value, such as the body of teacher
Height, the size in classroom, the very specific data parameters such as the position of camera and angle, these all make it that product seems inadequate intelligence
Energyization, Consumer's Experience can be had a strong impact in practice.
The content of the invention
Present invention aims at offer one kind can solve the problem that the above-mentioned problems in the prior art, simple in construction, connection
Convenient, analysis judges the data that two cameras transmit, and the switching action of multiple scape positions is controlled according to the data analyzed.
The object of the invention is achieved through the following technical solutions：
A kind of panorama position adaptive student graphical analysis control method, its system include embedded host, display, a panorama
Camera and a close shot camera, embedded host, which is used to analyze, judges the data that camera transmits, and is shown by display
Showing key frame, two cameras shoot student's panorama and close shot in classroom respectively, it is characterized in that, embedded host is for camera
The view data transmitted is recorded in real time, and rejects interference after being analyzed, if finding, target is stood up, and control camera is complete
Into the switching action between distant view and close shot, determine whether target sits down, into next work period.
Preferably, embedded host is as follows for the control and analysis of camera：
Control one, all student's actions in classroom are tracked and recorded, generate the image queue that can be recalled；
Control two, data caused by control one are assembled and split, multiple related thin objects are assembled into one
Complete moving target；Big target is split into by multiple moving targets according to body configuration's feature simultaneously, and abandons and does not meet
The big target of body configuration's feature；
Control three, the image queue of the target recorded in the target obtained by controlling in two and control one is subjected to union feature
Analysis, judges whether that obvious changing features do not occur for target in certain period of time, eliminate the target of significant change, with this
To avoid disturbing；
Control four, tracking target size analyze target to the distance of video camera, according to calculating the width that is moved when target is stood up
Degree；
Control five, the image queue of the target recorded in the target obtained by controlling in three and control one is subjected to joint point
Analysis, calculate operation amplitude and meet the target of result in control four, and be labeled as standing up and locked again；
Control six, locking are stood up after target, send panorama switching command, while are controlled and sent the rotation order of close shot camera, control
Close shot camera operation processed；
Control seven, according to close shot camera order feedback, after judging that close shot camera turns to specified location, send close shot switching
Order；
Control eight, if detecting that multiple targets are stood up, panorama switching command is sent, is switched to full-view camera；
Control nine, the target locked in control five is if there is downward operation, it is believed that target has been sat down；
Control ten, after student sits down, camera control power is surrendered, switches to other scenes.
Preferably, control one, using across frame difference comparison method, cross-domain 4 frame is compared to image difference, expands difference
Threshold value；Manner of comparison uses R, G, B difference maximum mode, as much as possible finds out the change that may occur；Gather 3*3 square
Battle array model carries out etching operation to the result of calculating, eliminates isolated noise, and then result is expanded using 5*5 matrix and grasped
Make, amplify changing value.
Preferably, control one is to throw away wrong data to being reentered into queue, generate the image team that can recall 2 seconds
Row.
Preferably, based on control one, control two is that the change that will be connected merges, and forms boundary rectangle；By institute
The boundary rectangle for having to obtain is mapped to a two-dimensional matrix, if two-dimensional matrix has been present, and the region of rectangle 70% is in two dimension
Corresponding to matrix in value, then the matrix is subjected to unique identification number, fractured operation is further carried out by big data.
Preferably, control three, carries out body configuration's feature judgement, using edge model to the rectangle for possessing unique mark
With head and shoulder backform shape, incongruent rectangle is rejected.
Preferably, control four, according to the distance of target to video camera, using the mode computation of conic section+correction value
Go out upper and lower, left, the left amplitude of motion.
Preferably, control five, multiframe judgement is carried out to the target in control one, if it exceeds the operation width in control four
Degree, then it is assumed that be target of alternatively standing up；Alternative target of standing up is subjected to multiframe feature judgement using reverse histogram mode, if
There is feature significantly change, then it is assumed that be interference, be otherwise target of really standing up, locked.
Preferably, the motion amplitude in control nine is more than 60% of result of calculation in control four, then it is assumed that sits down.
Preferably, described full-view camera and close shot camera is installed along with middle above classroom blackboard, adjust
Whole camera lens picture, quote whole classroom that can clap and be advisable；The upper edge of picture captured by full-view camera and close shot camera
No more than rear wall height 2.5 meters.
Compared with prior art, this product compared with the existing technology has advantages below and effect：This product is full-automatic
Adaptive analysis method, the technical scheme that any third party's auxiliary takes the photograph equipment is not installed, goes out student's by analysis of image content
Various actions, algorithm can be handled according to preset mode, reduce various human factors present in shooting by hand,
In the case of no manual intervention, auxiliary camera is tracked shooting.
Brief description of the drawings
Fig. 1 is the program switch logic flow chart of the present embodiment.
Embodiment
Illustrating the present invention below in conjunction with specific embodiment, the following example is merely to illustrate technical scheme,
Do not limit protection scope of the present invention.
Do firstly for several pictures in embodiment and illustrate：
Student's close shot：By close shot camera shooting at close range student's picture, student's expression, action are clearly visible.
Student's panorama：By the picture of the whole classroom student of distant view camera wide-long shot.
Hardware and installation instructions：
Its system includes embedded host, display, a full-view camera and a close shot camera, embedded host and is used for
Analysis judges the data that camera transmits, and shows key frame by display, and two cameras shoot student in classroom respectively
Panorama and close shot.2+2, video camera power lines of video line+2 are generally required, video camera can select any brand.
Full-view camera and close shot camera are installed along with middle above classroom blackboard, camera lens picture are adjusted, with energy
Whole classroom is quoted in bat to be advisable.The upper edge of picture captured by full-view camera and close shot camera is no more than rear wall height
2.5 rice.
The application foundation of the present embodiment method：
A) student's panorama, the picture of student's close shot among video camera be present；And student can be analyzed from these pictures
Stand up, action of sitting down.
B) resolution ratio of modern cameras 1080 is popularized very much, and obtained image degree of understanding is very high, enough images
Parser is used.
C) algorithm can be handled according to preset mode, reduce various human factors present in shooting by hand.
Embodiment：
As shown in figure 1, a kind of panorama position adaptive student graphical analysis control method of the present embodiment, its system includes embedded
Main frame, display, a full-view camera and a close shot camera, embedded host, which is used to analyze, judges what camera transmitted
Data, and key frame is shown by display, two cameras shoot student's panorama and close shot, embedded host in classroom respectively
Recorded in real time for the view data that camera transmits, and interference is rejected after being analyzed, target is stood up if finding, is controlled
Camera processed completes the switching action between distant view and close shot, determines whether target sits down, into next work week
Phase.
Specially：Embedded host is as follows for the control and analysis of camera：
Control one, all student's actions in classroom are tracked and recorded, generate the image queue that can be recalled；
Control two, data caused by control one are assembled and split, multiple related thin objects are assembled into one
Complete moving target；Big target is split into by multiple moving targets according to body configuration's feature simultaneously, and abandons and does not meet
The big target of body configuration's feature；
Control three, the image queue of the target recorded in the target obtained by controlling in two and control one is subjected to union feature
Analysis, judges whether that obvious changing features do not occur for target in certain period of time, eliminate the target of significant change, with this
To avoid disturbing；
Control four, tracking target size analyze target to the distance of video camera, according to calculating the width that is moved when target is stood up
Degree；
Control five, the image queue of the target recorded in the target obtained by controlling in three and control one is subjected to joint point
Analysis, calculate operation amplitude and meet the target of result in control four, and be labeled as standing up and locked again；
Control six, locking are stood up after target, send panorama switching command, while are controlled and sent the rotation order of close shot camera, control
Close shot camera operation processed；
Control seven, according to close shot camera order feedback, after judging that close shot camera turns to specified location, send close shot switching
Order；
Control eight, if detecting that multiple targets are stood up, panorama switching command is sent, is switched to full-view camera；
Control nine, the target locked in control five is if there is downward operation, it is believed that target has been sat down；
Control ten, after student sits down, camera control power is surrendered, switches to other scenes.
The control one of the present embodiment, using across frame difference comparison method, cross-domain 4 frame is compared to image difference, and it is poor to expand
Different threshold value；Manner of comparison uses R, G, B difference maximum mode, as much as possible finds out the change that may occur；Gather 3*3's
Matrix model carries out etching operation to the result of calculating, eliminates isolated noise, and then result is expanded using 5*5 matrix and grasped
Make, amplify changing value.
The control one of the present embodiment is to throw away wrong data to being reentered into queue, generate the image team that can recall 2 seconds
Row.
The present embodiment is based on control one, and control two is that the change that will be connected merges, and forms boundary rectangle；Will be all
Obtained boundary rectangle is mapped to a two-dimensional matrix, if two-dimensional matrix has been present, and the region of rectangle 70% is in Two-Dimensional Moment
Corresponding to battle array in value, then the matrix is subjected to unique identification number, fractured operation is further carried out by big data.
The control three of the present embodiment, body configuration's feature judgement is carried out to the rectangle for possessing unique mark, using edge mould
Type and head and shoulder backform shape, reject incongruent rectangle.
The control four of the present embodiment, according to the distance of target to video camera, using the mode computation of conic section+correction value
Go out upper and lower, left, the left amplitude of motion.
The control five of the present embodiment, multiframe judgement is carried out to the target in control one, if it exceeds the operation in control four
Amplitude, then it is assumed that be target of alternatively standing up；Alternative target of standing up is subjected to multiframe feature judgement using reverse histogram mode, such as
There is feature significantly change in fruit, then it is assumed that is interference, is otherwise target of really standing up, is locked.
Motion amplitude in the control nine of the present embodiment is more than 60% of result of calculation in control four, then it is assumed that sits down.
Disclosed above is only several specific embodiments of the application, but the application is not limited to this, any this area
Technical staff can think change, should all fall in the protection domain of the application.
Claims (10)
1. a kind of panorama position adaptive student graphical analysis control method, its system include embedded host, display, one it is complete
Scape camera and a close shot camera, embedded host, which is used to analyze, judges the data that camera transmits, and passes through display
Key frame is shown, two cameras shoot student's panorama and close shot in classroom respectively, it is characterized in that, embedded host is for shooting
The view data that head transmits is recorded in real time, and rejects interference after being analyzed, if finding, target is stood up, and controls camera
The switching action between distant view and close shot is completed, determines whether target sits down, into next work period.
2. panorama position adaptive student graphical analysis control method according to claim 1, it is characterized in that, embedded host
It is as follows for the control and analysis of camera：
Control one, all student's actions in classroom are tracked and recorded, generate the image queue that can be recalled；
Control two, data caused by control one are assembled and split, multiple related thin objects are assembled into one
Complete moving target；Big target is split into by multiple moving targets according to body configuration's feature simultaneously, and abandons and does not meet
The big target of body configuration's feature；
Control three, the image queue of the target recorded in the target obtained by controlling in two and control one is subjected to union feature
Analysis, judges whether that obvious changing features do not occur for target in certain period of time, eliminate the target of significant change, with this
To avoid disturbing；
Control four, tracking target size analyze target to the distance of video camera, according to calculating the width that is moved when target is stood up
Degree；
Control five, the image queue of the target recorded in the target obtained by controlling in three and control one is subjected to joint point
Analysis, calculate operation amplitude and meet the target of result in control four, and be labeled as standing up and locked again；
Control six, locking are stood up after target, send panorama switching command, while are controlled and sent the rotation order of close shot camera, control
Close shot camera operation processed；
Control seven, according to close shot camera order feedback, after judging that close shot camera turns to specified location, send close shot switching
Order；
Control eight, if detecting that multiple targets are stood up, panorama switching command is sent, is switched to full-view camera；
Control nine, the target locked in control five is if there is downward operation, it is believed that target has been sat down；
Control ten, after student sits down, camera control power is surrendered, switches to other scenes.
3. panorama position adaptive student graphical analysis control method according to claim 2, it is characterized in that, control one, adopt
With across frame difference comparison method, cross-domain 4 frame is compared to image difference, expands discrepancy threshold；Manner of comparison uses R, G, B difference
Maximum mode, as much as possible find out the change that may occur；Collection 3*3 matrix model corrodes to the result of calculating
Operation, eliminates isolated noise, then amplifies changing value to result expansive working using 5*5 matrix.
4. panorama position adaptive student's graphical analysis control method according to Claims 2 or 3, it is characterized in that, control one
It is to throw away wrong data to being reentered into queue, generate the image queue that can recall 2 seconds.
5. panorama position adaptive student graphical analysis control method according to claim 2, it is characterized in that, based on control
One, control two is that the change that will be connected merges, and forms boundary rectangle；All obtained boundary rectangles are mapped to one
Two-dimensional matrix, if two-dimensional matrix has been present, and the region of rectangle 70% is being worth corresponding to two-dimensional matrix, then by the matrix
Unique identification number is carried out, fractured operation is further carried out by big data.
6. panorama position adaptive student graphical analysis control method according to claim 2, it is characterized in that, control three is right
The rectangle for possessing unique mark carries out body configuration's feature judgement, using edge model and head and shoulder backform shape, rejects incongruent
Rectangle.
7. panorama position adaptive student graphical analysis control method according to claim 2, it is characterized in that, control four, root
According to the distance of target to video camera, upper and lower, left, the left amplitude of motion is gone out using the mode computation of conic section+correction value.
8. panorama position adaptive student graphical analysis control method according to claim 2, it is characterized in that, control five is right
Target in control one carries out multiframe judgement, if it exceeds the operation amplitude in control four, then it is assumed that be target of alternatively standing up；Will
Alternative target of standing up carries out multiframe feature judgement using reverse histogram mode, if there is feature significantly change, then it is assumed that be
Interference, is otherwise target of really standing up, is locked.
9. panorama position adaptive student graphical analysis control method according to claim 2, it is characterized in that, in control nine
Motion amplitude is more than 60% of result of calculation in control four, then it is assumed that sits down.
10. panorama position adaptive student graphical analysis control method according to claim 1, it is characterized in that, described is complete
Scape camera and close shot camera are installed along with middle above classroom blackboard, adjust camera lens picture, are quoted entirely with that can clap
Classroom is advisable；The upper edge of picture captured by full-view camera and close shot camera is no more than 2.5 meters of rear wall height.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710735501.8A CN107396059A (en) | 2017-08-24 | 2017-08-24 | A kind of panorama position adaptive student graphical analysis control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710735501.8A CN107396059A (en) | 2017-08-24 | 2017-08-24 | A kind of panorama position adaptive student graphical analysis control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107396059A true CN107396059A (en) | 2017-11-24 |
Family
ID=60345779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710735501.8A Pending CN107396059A (en) | 2017-08-24 | 2017-08-24 | A kind of panorama position adaptive student graphical analysis control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107396059A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021034A (en) * | 2019-03-20 | 2019-07-16 | 华南理工大学 | A kind of tracking recording broadcasting method and system based on head and shoulder detection |
| CN111131713A (en) * | 2019-12-31 | 2020-05-08 | 深圳市维海德技术股份有限公司 | Lens switching method, device, equipment and computer readable storage medium |
| CN112887600A (en) * | 2021-01-25 | 2021-06-01 | 睿魔智能科技（深圳）有限公司 | Shooting method and system based on standing behavior detection |
| CN115396602A (en) * | 2022-07-30 | 2022-11-25 | 珠海视熙科技有限公司 | Scene shooting control method, device and system based on three-camera system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103281492A (en) * | 2013-05-23 | 2013-09-04 | 深圳锐取信息技术股份有限公司 | Video picture switching method, video picture switching system, recording and broadcasting server and video recording and broadcasting system |
| CN103327250A (en) * | 2013-06-24 | 2013-09-25 | 深圳锐取信息技术股份有限公司 | Method for controlling camera lens based on pattern recognition |
| CN104823438A (en) * | 2012-09-13 | 2015-08-05 | 通用电气公司 | System and method for generating activity summary of person |
| CN105139702A (en) * | 2015-10-14 | 2015-12-09 | 广州天莱软件科技有限公司 | Recording and broadcasting system used for teaching and use method thereof |
| CN105611237A (en) * | 2015-12-22 | 2016-05-25 | 杭州凡龙科技有限公司 | Method for simulating five cameras by utilizing double cameras for education recording and broadcasting |
-
2017
- 2017-08-24 CN CN201710735501.8A patent/CN107396059A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104823438A (en) * | 2012-09-13 | 2015-08-05 | 通用电气公司 | System and method for generating activity summary of person |
| CN103281492A (en) * | 2013-05-23 | 2013-09-04 | 深圳锐取信息技术股份有限公司 | Video picture switching method, video picture switching system, recording and broadcasting server and video recording and broadcasting system |
| CN103327250A (en) * | 2013-06-24 | 2013-09-25 | 深圳锐取信息技术股份有限公司 | Method for controlling camera lens based on pattern recognition |
| CN105139702A (en) * | 2015-10-14 | 2015-12-09 | 广州天莱软件科技有限公司 | Recording and broadcasting system used for teaching and use method thereof |
| CN105611237A (en) * | 2015-12-22 | 2016-05-25 | 杭州凡龙科技有限公司 | Method for simulating five cameras by utilizing double cameras for education recording and broadcasting |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021034A (en) * | 2019-03-20 | 2019-07-16 | 华南理工大学 | A kind of tracking recording broadcasting method and system based on head and shoulder detection |
| CN111131713A (en) * | 2019-12-31 | 2020-05-08 | 深圳市维海德技术股份有限公司 | Lens switching method, device, equipment and computer readable storage medium |
| CN111131713B (en) * | 2019-12-31 | 2022-03-08 | 深圳市维海德技术股份有限公司 | Lens switching method, device, equipment and computer readable storage medium |
| CN112887600A (en) * | 2021-01-25 | 2021-06-01 | 睿魔智能科技（深圳）有限公司 | Shooting method and system based on standing behavior detection |
| CN112887600B (en) * | 2021-01-25 | 2022-08-05 | 睿魔智能科技（深圳）有限公司 | Shooting method and system based on standing behavior detection |
| CN115396602A (en) * | 2022-07-30 | 2022-11-25 | 珠海视熙科技有限公司 | Scene shooting control method, device and system based on three-camera system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103716594B (en) | Panorama splicing linkage method and device based on moving target detecting | |
| CN107396059A (en) | A kind of panorama position adaptive student graphical analysis control method | |
| CN103716595B (en) | Panoramic mosaic video camera and ball machine inter-linked controlling method and device | |
| CN108419014B (en) | Method for capturing human face by linkage of panoramic camera and multiple capturing cameras | |
| CN109151439B (en) | Automatic tracking shooting system and method based on vision | |
| CN100551048C (en) | Multiple-camera supervisory control system and tracking thereof based on the three-dimensional video-frequency dynamic tracking | |
| CN103761514B (en) | The system and method for recognition of face is realized based on wide-angle gunlock and many ball machines | |
| CN101860732B (en) | Method of controlling holder camera to automatically track target | |
| CN105578044A (en) | Panoramic view adaptive teacher image analysis method | |
| CN103780837B (en) | A kind of motion detection and the method and its device of positioning shooting | |
| CN104574359A (en) | Student tracking and positioning method based on primary and secondary cameras | |
| CN111242025B (en) | Real-time action monitoring method based on YOLO | |
| CN108319918B (en) | Embedded tracker and target tracking method applied to same | |
| JP2012040071A (en) | Baseball training system | |
| CN105611237A (en) | Method for simulating five cameras by utilizing double cameras for education recording and broadcasting | |
| CN106780550A (en) | A kind of method for tracking target and electronic equipment | |
| CN107861625A (en) | Gaze tracking system and method based on 3d space model | |
| CN105069795A (en) | Moving object tracking method and apparatus | |
| Bernardin et al. | Automatic person detection and tracking using fuzzy controlled active cameras | |
| CN106991358A (en) | The algorithm that automatic identification football match based on panoramic video is scored | |
| CN113838098A (en) | Intelligent tracking shooting system for remote high-speed moving target | |
| CN114495068A (en) | Road surface health detection 'element' method based on man-machine interaction and deep learning | |
| CN103546679B (en) | Device and method for reducing separation of shot object from shooting window | |
| CN101895685A (en) | Video capture control device and method | |
| US20150189191A1 (en) | Process and system for video production and tracking of objects |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |