CN107220608A - What a kind of basketball action model was rebuild and defended instructs system and method - Google Patents

What a kind of basketball action model was rebuild and defended instructs system and method Download PDF

Info

Publication number
CN107220608A
CN107220608A CN201710362557.3A CN201710362557A CN107220608A CN 107220608 A CN107220608 A CN 107220608A CN 201710362557 A CN201710362557 A CN 201710362557A CN 107220608 A CN107220608 A CN 107220608A
Authority
CN
China
Prior art keywords
basketball
action
depth
basketball action
rebuild
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
Application number
CN201710362557.3A
Other languages
Chinese (zh)
Other versions
CN107220608B (en
Inventor
张东
张天
魏伟和
黄天宇
胡竞涛
成斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN201710362557.3A priority Critical patent/CN107220608B/en
Publication of CN107220608A publication Critical patent/CN107220608A/en
Application granted granted Critical
Publication of CN107220608B publication Critical patent/CN107220608B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/23—Recognition of whole body movements, e.g. for sport training
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B69/00—Training appliances or apparatus for special sports
    • A63B69/0071—Training appliances or apparatus for special sports for basketball
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Psychiatry (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Image Analysis (AREA)
  • Prostheses (AREA)

Abstract

What a kind of basketball action model disclosed by the invention was rebuild and defended instructs system, includes completing Kinect depth transducers, the deep learning module that basketball action message is extracted, and basketball movement posture rebuilds module；Wherein deep learning module, is classified by deep learning to basketball action, and the coordinate value of the camera coordinates system by the depth value corresponding to the basketball action bone coordinate points in a series of pictures, in Kinect depth transducers is preserved；Basketball movement posture rebuilds module, according to the three-dimensional coordinate of the skeletal joint point of preservation, and the basketball action complete to one is rebuild；Instructed accordingly in training athlete.Present invention combination depth learning technology, realizes identification and the statistics of basic basketball action.

Description

What a kind of basketball action model was rebuild and defended instructs system and method
Technical field
The present invention relates to deep learning detection field, the guidance system that more particularly to a kind of basketball action model is rebuild and defended System and method.
Background technology
At present, the development of Kinect sensor technology, promotes model reconstruction technology, but prior art is simply done to people As being detected, basketball field is not applied to, allows true man targetedly to defend reconstruction model.
The content of the invention
Rebuild it is an object of the invention to the shortcoming and deficiency for overcoming prior art there is provided a kind of basketball action model and anti- That keeps instructs system, and the system can obtain more accurate basketball action message, so as to carry out the model reconstruction in space, Targetedly trained for sportsman.
Another object of the present invention is to provide the guidance method that a kind of basketball action model is rebuild and defended.
The purpose of the present invention is realized by following technical scheme：
What a kind of basketball action model was rebuild and defended instructs system, including Kinect depth transducers, deep learning mould Block, and basketball movement posture rebuild module；Wherein
Kinect depth transducers, for extracting the complete basketball action cromogram of sportsman, basketball action skeleton character, basket Ball acts the depth information of skeletal joint point；
Deep learning module, by deep learning, after being trained to the action of correct basketball, obtains weight, so that right Basketball action is classified；Then the basketball action cromogram of input is identified, if the basketball required for recognizing is moved Make, and then the corresponding basketball action skeleton character of basketball action and basketball action bone are extracted by Kinect depth transducers The depth information of artis；Thus the complete basketball action pictures of successive frame are obtained, the basketball in a series of pictures is acted Depth value corresponding to bone coordinate points, the coordinate value of the camera coordinates system in Kinect depth transducers are preserved；
Basketball movement posture rebuilds module, according to the three-dimensional coordinate of the skeletal joint point of preservation, the basketball complete to one Action is rebuild；Sportsman simulates the model of corresponding basketball action when carrying out the training of corresponding basketball action, allows motion Member's trunk skeletal joint point is trained under identical depth, according to carrying for the three-dimensional coordinate of the skeletal joint point to sportsman Take, thus predict the action of corresponding basketball whether standard.
Because majority are in motion, with specific muscle memory, so, most of sportsmen are shooting and broken through When, can all there is identical movement range, defender is according to model, and training is anti-punctual, carry out block and grab required defence Memory, can provide help for real racetrack.
The deep learning, refers to based on the deep learning method under yolo frameworks.It can accurately find sportsman's Position and tell basketball action.
The basketball action includes block, shoots, grabs.
Another object of the present invention is realized by following technical scheme：
The guidance method that a kind of basketball action model is rebuild and defended, is comprised the steps of：
S1, the complete basketball action cromogram of extraction sportsman, basketball action skeleton character, basketball act skeletal joint point Depth information；
S2, by deep learning, after being trained to the action of correct basketball, obtain weight, thus basketball is acted into Row classification；Then the basketball action cromogram of input is identified, if the basketball action required for recognizing, and then pass through Kinect depth transducers extract the basketball and act the depth that corresponding basketball action skeleton character and basketball act skeletal joint point Spend information；Thus the complete basketball action pictures of successive frame are obtained, the basketball in a series of pictures is acted into bone coordinate points Corresponding depth value, the coordinate value of the camera coordinates system in Kinect depth transducers are preserved；
S3, the three-dimensional coordinate according to the skeletal joint point of preservation, the basketball action complete to one are rebuild；Sportsman When carrying out the training of corresponding basketball action, the model of corresponding basketball action is simulated, allows sportsman's trunk skeletal joint point to exist It is trained under identical depth, according to the extraction of the three-dimensional coordinate of the skeletal joint point to sportsman, so as to predict corresponding Basketball action whether standard.
The present invention compared with prior art, has the following advantages that and beneficial effect：
(1) present invention uses Kinect sensor technology, it is only necessary to three-dimensional coordinate, is achieved that the basket to required research Ball acts more accurate model reconstruction.
(2) present invention can allow sportsman to have more targetedly defence training.
(3) present invention need not install any body-sensing sensor with institute onlooker.
(4) present invention improves the efficiency recognized to colour picture by deep learning detection technique.
Brief description of the drawings
The flow chart for the guidance method that Fig. 1 rebuilds and defended for a kind of basketball action model of the present invention.
Fig. 2 is the depth information for the basketball action skeletal joint point extracted under Kinect depth transducers.
Fig. 3 acts skeleton character figure for the basketball extracted under Kinect depth transducers.
Embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited In this.
As shown in Figure 1, it is desirable to which basketball movement posture is rebuild, by Kinect depth transducers, obtain basketball and move Make cromogram information, basketball action depth map information and basketball action skeleton character.Gather extensive standard basketball action, base In yolo frameworks, the weight needed is trained, so as to classify to basketball action, finally instructs defender to carry out special instruction Practice.
As shown in Fig. 2 detected person does act of shooting, by the detection of deep learning, extract be considered as into The higher continuous a few frame pictures of row act of shooting possibility, obtain the three-dimensional coordinate of skeletal joint point.So as to just obtain Basic model.Defender when carrying out block training, just can virtually simulate and be thrown under Kinect depth transducers A series of model of basketballs action of basket person, allows trainer's trunk skeletal joint point to be trained under identical depth, according to Whether the extraction to the three-dimensional coordinate of the skeletal joint point of defender, success is defended so as to predict.Because majority are in motion When, with specific muscle memory, so, most of sportsmen can have identical movement range in shooting and breakthrough, prevent The person of keeping is according to model, and training is anti-punctual, the defence memory required for carrying out block and grabbing, and can provide side for real racetrack Help.
Above-described embodiment is preferably embodiment, but embodiments of the present invention are not by above-described embodiment of the invention Limitation, other any Spirit Essences without departing from the present invention and the change made under principle, modification, replacement, combine, simplification, Equivalent substitute mode is should be, is included within protection scope of the present invention.

Claims (4)

  1. What 1. a kind of basketball action model was rebuild and defended instructs system, it is characterised in that：Including Kinect depth transducers, depth Study module is spent, and basketball movement posture rebuilds module；Wherein
    Kinect depth transducers, are moved for extracting the complete basketball action cromogram of sportsman, basketball action skeleton character, basketball Make the depth information of skeletal joint point；
    Deep learning module, by deep learning, after being trained to the action of correct basketball, obtains weight, so as to basketball Action is classified；Then the basketball action cromogram of input is identified, if the basketball action required for recognizing, enters And the basketball is extracted by Kinect depth transducers and acts corresponding basketball action skeleton character and basketball action skeletal joint The depth information of point；Thus the complete basketball action pictures of successive frame are obtained, the basketball in a series of pictures is acted into bone Depth value corresponding to coordinate points, the coordinate value of the camera coordinates system in Kinect depth transducers are preserved；
    Basketball movement posture rebuilds module, according to the three-dimensional coordinate of the skeletal joint point of preservation, the basketball action complete to one Rebuild；Sportsman simulates the model of corresponding basketball action when carrying out the training of corresponding basketball action, allows sportsman master Dry skeletal joint point is trained under identical depth, according to the extraction of the three-dimensional coordinate of the skeletal joint point to sportsman, So as to predict the action of corresponding basketball whether standard.
  2. What 2. basketball action model was rebuild and defended according to claim 1 instructs system, it is characterised in that：The depth Practise, refer to based on the deep learning method under yolo frameworks.
  3. What 3. basketball action model was rebuild and defended according to claim 1 instructs system, it is characterised in that：The basketball is moved Work includes block, shoots, grabs.
  4. 4. the one kind for instructing system rebuild and defended based on basketball action model described in claims 1 to 3 any claim The guidance method that basketball action model is rebuild and defended, is comprised the steps of：
    S1, the complete basketball action cromogram of extraction sportsman, basketball action skeleton character, basketball act the depth of skeletal joint point Information；
    S2, by deep learning, after being trained to the action of correct basketball, weight is obtained, so as to be divided basketball action Class；Then the basketball action cromogram of input is identified, if the basketball action required for recognizing, and then pass through Kinect depth transducers extract the basketball and act the depth that corresponding basketball action skeleton character and basketball act skeletal joint point Spend information；Thus the complete basketball action pictures of successive frame are obtained, the basketball in a series of pictures is acted into bone coordinate points Corresponding depth value, the coordinate value of the camera coordinates system in Kinect depth transducers are preserved；
    S3, the three-dimensional coordinate according to the skeletal joint point of preservation, the basketball action complete to one are rebuild；Sportsman is entering During the training of the corresponding basketball action of row, the model of corresponding basketball action is simulated, sportsman's trunk skeletal joint point is allowed identical Depth under be trained, according to the extraction of the three-dimensional coordinate of the skeletal joint point to sportsman, so as to predict corresponding basketball Action whether standard.
CN201710362557.3A 2017-05-22 2017-05-22 Basketball action model reconstruction and defense guidance system and method Expired - Fee Related CN107220608B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710362557.3A CN107220608B (en) 2017-05-22 2017-05-22 Basketball action model reconstruction and defense guidance system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710362557.3A CN107220608B (en) 2017-05-22 2017-05-22 Basketball action model reconstruction and defense guidance system and method

Publications (2)

Publication Number Publication Date
CN107220608A true CN107220608A (en) 2017-09-29
CN107220608B CN107220608B (en) 2021-06-08

Family

ID=59944835

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710362557.3A Expired - Fee Related CN107220608B (en) 2017-05-22 2017-05-22 Basketball action model reconstruction and defense guidance system and method

Country Status (1)

Country Link
CN (1) CN107220608B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909060A (en) * 2017-12-05 2018-04-13 前海健匠智能科技（深圳）有限公司 Gymnasium body-building action identification method and device based on deep learning
CN109821243A (en) * 2019-01-25 2019-05-31 丰羽教育科技（上海）有限公司 A method of simulation reappears shooting process
CN109948459A (en) * 2019-02-25 2019-06-28 广东工业大学 A kind of football movement appraisal procedure and system based on deep learning
CN110478883A (en) * 2019-08-21 2019-11-22 南京信息工程大学 A kind of body-building movement teaching and correction system and method
CN110960843A (en) * 2019-12-23 2020-04-07 天水师范学院 Basketball skill auxiliary training system
CN111569398A (en) * 2020-05-09 2020-08-25 深圳市洲明科技股份有限公司 Semi-immersion type bowling training system and method based on LED display screen
CN117475514A (en) * 2023-11-10 2024-01-30 广州市微锋科技有限公司 Shooting training system and method based on image analysis

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130172058A1 (en) * 2007-05-24 2013-07-04 Pillar Vision, Inc. Method and apparatus for video game simulations using motion capture
US20140094307A1 (en) * 2012-10-01 2014-04-03 Microsoft Corporation Multi-camera depth imaging
US20140198954A1 (en) * 2011-07-28 2014-07-17 Adrian BULZACKI Systems and methods of detecting body movements using globally generated multi-dimensional gesture data
WO2014194337A1 (en) * 2013-05-30 2014-12-04 Atlas Wearables, Inc. Portable computing device and analyses of personal data captured therefrom
CN104850846A (en) * 2015-06-02 2015-08-19 深圳大学 Human behavior recognition method and human behavior recognition system based on depth neural network
CN104899561A (en) * 2015-05-27 2015-09-09 华南理工大学 Parallelized human body behavior identification method
CN105512621A (en) * 2015-11-30 2016-04-20 华南理工大学 Kinect-based badminton motion guidance system
CN106022213A (en) * 2016-05-04 2016-10-12 北方工业大学 Human body motion recognition method based on three-dimensional bone information
CN105999670A (en) * 2016-05-31 2016-10-12 山东科技大学 Shadow-boxing movement judging and guiding system based on kinect and guiding method adopted by same
US20170098125A1 (en) * 2015-10-05 2017-04-06 Alan W. Marty Systems and methods for monitoring objects in athletic playing spaces
CN106581949A (en) * 2016-11-24 2017-04-26 石家庄铁路职业技术学院 Basketball shooting training evaluation system
CN106650687A (en) * 2016-12-30 2017-05-10 山东大学 Posture correction method based on depth information and skeleton information
CN106650562A (en) * 2016-06-14 2017-05-10 西安电子科技大学 Online continuous human behavior identification method based on Kinect

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130172058A1 (en) * 2007-05-24 2013-07-04 Pillar Vision, Inc. Method and apparatus for video game simulations using motion capture
US20140198954A1 (en) * 2011-07-28 2014-07-17 Adrian BULZACKI Systems and methods of detecting body movements using globally generated multi-dimensional gesture data
US20140094307A1 (en) * 2012-10-01 2014-04-03 Microsoft Corporation Multi-camera depth imaging
WO2014194337A1 (en) * 2013-05-30 2014-12-04 Atlas Wearables, Inc. Portable computing device and analyses of personal data captured therefrom
CN104899561A (en) * 2015-05-27 2015-09-09 华南理工大学 Parallelized human body behavior identification method
CN104850846A (en) * 2015-06-02 2015-08-19 深圳大学 Human behavior recognition method and human behavior recognition system based on depth neural network
US20170098125A1 (en) * 2015-10-05 2017-04-06 Alan W. Marty Systems and methods for monitoring objects in athletic playing spaces
CN105512621A (en) * 2015-11-30 2016-04-20 华南理工大学 Kinect-based badminton motion guidance system
CN106022213A (en) * 2016-05-04 2016-10-12 北方工业大学 Human body motion recognition method based on three-dimensional bone information
CN105999670A (en) * 2016-05-31 2016-10-12 山东科技大学 Shadow-boxing movement judging and guiding system based on kinect and guiding method adopted by same
CN106650562A (en) * 2016-06-14 2017-05-10 西安电子科技大学 Online continuous human behavior identification method based on Kinect
CN106581949A (en) * 2016-11-24 2017-04-26 石家庄铁路职业技术学院 Basketball shooting training evaluation system
CN106650687A (en) * 2016-12-30 2017-05-10 山东大学 Posture correction method based on depth information and skeleton information

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
CHIH-HSIEN HSIA等: ""ANALYSES OF BASKETBALL PLAYER FIELD GOAL SHOOTING POSTURES FOR PLAYER MOTION CORRECTION USING KINECT SENSOR"", 《2014 INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ISPACS)》 *
JAVED IMRAN: ""Human action recognition using RGB-D sensor and deep convolutional neural networks"", 《2016 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI)》 *
JING ZHANG等: ""RGB-D-based action recognition datasets: A survey"", 《PATTERN RECOGNITION》 *
ZHAOFU QIU: ""The Development of Basketball Assistant Training System Based on Kinect Motion Capture"", 《ADVANCED MATERIALS RESEARCH》 *
张典华等: ""多平台三维篮球运动仿真系统的设计与实现"", 《计算机工程与设计》 *
徐涛等: ""基于Kinect体感设备投篮系统设计"", 《山东工业技术》 *
邓小园: ""基于Kinect运动捕捉的高尔夫挥杆分析与辅助训练系统的研制"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107909060A (en) * 2017-12-05 2018-04-13 前海健匠智能科技（深圳）有限公司 Gymnasium body-building action identification method and device based on deep learning
CN109821243A (en) * 2019-01-25 2019-05-31 丰羽教育科技（上海）有限公司 A method of simulation reappears shooting process
CN109948459A (en) * 2019-02-25 2019-06-28 广东工业大学 A kind of football movement appraisal procedure and system based on deep learning
CN109948459B (en) * 2019-02-25 2023-08-25 广东工业大学 Football action evaluation method and system based on deep learning
CN110478883A (en) * 2019-08-21 2019-11-22 南京信息工程大学 A kind of body-building movement teaching and correction system and method
CN110960843A (en) * 2019-12-23 2020-04-07 天水师范学院 Basketball skill auxiliary training system
CN111569398A (en) * 2020-05-09 2020-08-25 深圳市洲明科技股份有限公司 Semi-immersion type bowling training system and method based on LED display screen
CN111569398B (en) * 2020-05-09 2022-01-04 深圳市洲明科技股份有限公司 Semi-immersion type bowling training system and method based on LED display screen
CN117475514A (en) * 2023-11-10 2024-01-30 广州市微锋科技有限公司 Shooting training system and method based on image analysis

Also Published As

Publication number Publication date
CN107220608B (en) 2021-06-08

Similar Documents

Publication Publication Date Title
CN107220608A (en) What a kind of basketball action model was rebuild and defended instructs system and method
US20200193671A1 (en) Techniques for rendering three-dimensional animated graphics from video
KR102106135B1 (en) Apparatus and method for providing application service by using action recognition
CN110705390A (en) Body posture recognition method and device based on LSTM and storage medium
CN205537314U (en) 3D virtual reality is training system under battle conditions
CN109564621A (en) System and method for the tracking fortune band in movement environment
CN106599770A (en) Skiing scene display method based on body feeling motion identification and image matting
CN105825268A (en) Method and system for data processing for robot action expression learning
CN107330967A (en) Knight's athletic posture based on inertia sensing technology is caught and three-dimensional reconstruction system
CN110427900A (en) A kind of method, apparatus and equipment of intelligent guidance body-building
CN104353240A (en) Running machine system based on Kinect
KR100907704B1 (en) Golfer's posture correction system using artificial caddy and golfer's posture correction method using it
US11568617B2 (en) Full body virtual reality utilizing computer vision from a single camera and associated systems and methods
CN105749525A (en) Basketball training device based on AR technology
CN107930048A (en) A kind of space somatosensory recognition motion analysis system and method for motion analysis
CN104248835A (en) Intelligent basketball scoring system and work method thereof
CN113476815A (en) Intelligent sports auxiliary training method and system based on E-ink
Yang et al. Research on face recognition sports intelligence training platform based on artificial intelligence
CN112007343A (en) Double-arm boxing training robot
CN109407826A (en) Ball game analogy method, device, storage medium and electronic equipment
CN103218826B (en) Projectile based on Kinect detection, three-dimensional localization and trajectory predictions method
CN101266118A (en) Shooting training system adopting simulated inverse attack
Pan et al. Study on automatic tracking method of marking points in sports image sequence
Wang Basketball sports posture recognition based on neural computing and visual sensor
CN205598586U (en) Basketball training device based on AR technique

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
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210608