CN103106411A - Tennis motion capturing and analyzing method - Google Patents
Tennis motion capturing and analyzing method Download PDFInfo
- Publication number
- CN103106411A CN103106411A CN2012105376286A CN201210537628A CN103106411A CN 103106411 A CN103106411 A CN 103106411A CN 2012105376286 A CN2012105376286 A CN 2012105376286A CN 201210537628 A CN201210537628 A CN 201210537628A CN 103106411 A CN103106411 A CN 103106411A
- Authority
- CN
- China
- Prior art keywords
- tennis
- motion
- tennis racket
- data
- proper vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
A tennis motion capturing and analyzing method is characterized by comprising the steps of binding a mark point and a tennis racket, installing a camera on the dead ahead of a motion area, wherein the camera is used for capturing images of a motion area and obtaining inertia parameters of motion of the tennis racket mark point, collecting a digital image of the tennis racket, inputting the digital image to a general-purpose computer, obtaining a digital video image of motion of the tennis racket, collecting the inertia parameters of the motion of the tennis racket mark point, resolving the collected inertia parameters and the digital video image, fusing data of multiple sensors, obtaining a motion mode of the tennis racket mark point, identifying a motion pattern according to the motion mode of the tennis racket mark point, and identifying and analyzing captured motions.
Description
Technical field
The invention belongs to computer image processing technology, motion capture analytic technique and virtual reality technology crossing domain, especially relate to a kind of tennis motion capture and analytic method.
Background technology
At present, the CN1662283 of SSD Co., Ltd. discloses a kind of tennis game system, this system comprises by the AV cable and is connected to the game machine of television receiver and the racket type input media of operation input is provided to this game machine, and the player plays ball by operating the batting side tennis player who shows on this racket type input media indication monitor picture.At this moment, what game processor that game machine comprises calculated the other side tennis player returns the ball predicted position, and batting side tennis player's that will be at this moment present position and its prediction are returned ball position and are made comparisons, judgement prediction is returned ball position whether in batting side tennis player's batting possible range, if this judgment means is judged as outside the batting possible range, the batter's box mobile device is that game processor moves batter's box.
At present, be inertia tracer technique and optical tracking technology in field of human-computer interaction motion tracking technology relatively more commonly used.Inertia tracer technique characteristics are to realize simply, strong interference immunity; Shortcoming is to obtain all sidedly the motion feature of tracked target, can only finite sum reflects partly the movement characteristic of tracked target.The optical tracking technical characterstic is the motion conditions that can reflect all sidedly object, and precision is high; Shortcoming is to realize comparatively difficulty, and the scope of following the trail of is less.Foregoing invention has all only been used a certain single technology wherein, and its Technology origin is single, and shortcoming is obvious.
Summary of the invention
The purpose of this invention is to provide a kind of virtual reality technology and optical tracking of utilizing and follow the trail of with inertia the method that combines, reduce the complexity of motion recognition system, improve stability and the anti-interference of motion recognition system, effectively enlarge the motion tracking scope and in time feed back movable information, collection and the processing of special exercise information in realizing in a big way, and it is applied to tennis motion capture and parsing, for the application of virtual reality technology in human-computer interaction tennis teaching and training provides solution.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of tennis motion capture and analytic method comprise the following steps:
A, with the binding of gauge point and tennis racket, camera is arranged on the dead ahead of moving region, be used for catching the moving region image, obtain the inertial parameter of tennis racket gauge point motion;
The digital picture of B, collection tennis racket is also inputted multi-purpose computer, obtains the digital video image of tennis racket motion; Gather the inertial parameter of tennis racket gauge point motion;
C, to the inertial parameter that gathers with digital video image resolves and Fusion, obtain tennis racket gauge point mode of motion;
D, identify its pattern according to tennis racket gauge point mode of motion, identification and parsing are carried out in the action of catching.
Described step C also comprises: resolve algorithm by adopting corresponding sensor signal Preprocessing Algorithm and athletic posture, utilize the inertial parameter that collects to calculate instantaneous acceleration, speed, position and the attitude of the relative earth of target; According to the digital video image that collects, at first the present invention extracts tennis racket motion characteristics compositions by two value-based algorithms, and characteristic composition is asked for its center of gravity, obtains the characteristic composition center; Then according to the calculating to selected feature, set up the corresponding relation between feature; According to the corresponding relation between feature, according to BuBumblebee binocular measuring principle, realize that Three dimensional Targets accurately locates; To tennis racket gauge point mode of motion and the inertial parameter that obtains in described step B, by the Multisensor Data Fusion Algorithm of D-S evidence theory, obtain reflecting the consistent data of tennis racket motion feature.
Described step D also comprises:
D1, gather various tennis racket motion sample pattern data, the sample pattern data of pre-collection are marked;
D2, go out to reflect one by one the proper vector of tennis racket motion essence feature from described sample pattern extracting data;
D3, divide according to described proper vector under category regions, make the proper vector that only comprises similar sample in each the different classes of zone after division, set up the sorter from proper vector to mapping relations affiliated classification;
D4, tennis pattern data to be detected are processed, extracted its proper vector;
D5, the proper vector of pattern data to be detected is input to described sorter, sorter is differentiated according to its proper vector, obtains the identification result to these pattern data to be detected, and identification result is carried out Action Semantic resolve.
Described step D2 also comprises:
D21, described sample pattern data are carried out pre-service, obtain the tennis action data;
D22, extract the characteristic component of its essential characteristic of reflection from the tennis action data;
D23, described characteristic component is made up, obtain described proper vector.
Described step D4 also comprises:
D41, described tennis pattern data to be identified are carried out pre-service, obtain Identification Data;
D42, extract the characteristic component of reflection Identification Data essential characteristic from Identification Data;
D43, described characteristic component is made up, obtain described proper vector.
Beneficial effect of the present invention: owing to having adopted inertia to follow the trail of and optical tracking dual mode concentrated expression target travel situation, effectively enlarged tracking range, improved the precision of measuring, solve inertia and followed the trail of the poor problem of tennis action recognition, susceptibility that to obtain the tennis Global Information, can not do complexity, also solved the problem that optical tracking technology rediscover is poor, effective tracking range is little and stop impact simultaneously.The present invention also has very strong practicality, can catch and resolve the tennis action, for the human-computer interaction and the exploitation of all kinds of tennis virtual reality sports applications that realize tennis are laid a good foundation.
Below with reference to drawings and Examples, the present invention is described in detail.
Description of drawings
Fig. 1 is tennis motion capture of the present invention, analytic method schematic block diagram;
Fig. 2 is tennis action data acquisition method schematic block diagram of the present invention;
Fig. 3 is tennis action data acquisition methods schematic block diagram of the present invention;
Fig. 4 is tennis action identifying of the present invention and analytic method schematic block diagram;
Fig. 5 is one-piece construction schematic block diagram of the present invention.
Embodiment
Below the better embodiment of the present invention is described in detail.As shown in Figure 1, the present invention includes three modules during enforcement, respectively exercise data acquisition module 1, motion capture module 2, tennis action identifying and parsing module 3, the present invention can be used for tennis motion capture and parsing, for the human-computer interaction and the exploitation of all kinds of tennis virtual reality sports applications that realize tennis are laid a good foundation.
The present invention is a kind of tennis motion capture, analytic method as Fig. 2-5, comprises the following steps:
A, sportsman hold tennis racket and comprise at least two cameras at described camera 14() positive motion, to measure one group of inertial parameter with the described micro inertial measurement unit 11 of racket binding, inertial parameter extraction unit 13 is sent to described movable information by wireless transport module and resolves unit 23; Simultaneously video capture device is caught the set of number image of described specific wavelength pointolite 12, and it is sent to described image characteristics extraction unit 21;
B, movable information resolve 23 pairs of unit institute's inertial parameter that obtains and adopt corresponding sensor signal Preprocessing Algorithm and athletic posture to resolve algorithm, calculate instantaneous acceleration, speed, position and the attitude of the relative earth of target, and result is sent to Fusion unit 24; 21 pairs of the image characteristics extraction unit video image that obtains carries out the characteristic composition that two value-based algorithms obtain tested racket, three-dimensional fix unit 22 is according to BuBumblebee binocular measuring principle, obtain the three dimensional space coordinate of racket identification point, and be sent to Fusion unit 24; Fusion unit 24 adopts the data message that obtains based on the Multisensor Data Fusion Algorithm of D-S evidence theory inertial parameter and the three dimensional space coordinate to tested racket and deals with, and obtains the pattern data of tested racket;
C, gather tennis pattern sample data in enormous quantities, various in advance, obtain the relevant action sample.31 pairs of sample mode data of training module are carried out pre-service, obtain training data.Sorter in Fig. 4 extracts the proper vector of reflection data essential characteristic and according to proper vector, it is classified from training data, set up the sorter from proper vector to mapping relations affiliated classification; The pattern data to be detected that 32 pairs of identification and resolution unit are caught are carried out pre-service, obtain Identification Data, extract proper vector and be input in the described sorter of Fig. 4 from Identification Data, sorter is differentiated according to its proper vector, obtain the identification result to pattern data to be detected, again identification result is carried out the semantic parsing of relevant action, use for later stage application and development or motion analysis.
Claims (8)
1. a tennis motion capture and analytic method, is characterized in that, comprises the following steps:
A, with the binding of gauge point and tennis racket, camera is arranged on the dead ahead of moving region, be used for catching the moving region image, obtain the inertial parameter of tennis racket gauge point motion;
The digital picture of B, collection tennis racket is also inputted multi-purpose computer, obtains the digital video image of tennis racket motion; Gather the inertial parameter of tennis racket gauge point motion;
C, to the inertial parameter that gathers with digital video image resolves and Fusion, obtain tennis racket gauge point mode of motion;
D, identify its pattern according to tennis racket gauge point mode of motion, identification and parsing are carried out in the action of catching.
2. a kind of tennis motion capture as claimed in claim 1 and analytic method, it is characterized in that, described step C also comprises: resolve algorithm by adopting corresponding sensor signal Preprocessing Algorithm and athletic posture, utilize the inertial parameter that collects to calculate instantaneous acceleration, speed, position and the attitude of the relative earth of target.
3. a kind of tennis motion capture as claimed in claim 1 and analytic method, it is characterized in that, described step C also comprises: according to the digital video image that collects, at first the present invention extracts tennis racket motion characteristics composition by two value-based algorithms, characteristic composition is asked for its center of gravity, obtain the characteristic composition center; Then according to the calculating to selected feature, set up the corresponding relation between feature.
4. a kind of tennis motion capture as claimed in claim 3 and analytic method, is characterized in that, described step C also comprises: according to the corresponding relation between feature, according to BuBumblebee binocular measuring principle, realize that Three dimensional Targets accurately locates.
5. a kind of tennis motion capture as claimed in claim 1 and analytic method, it is characterized in that, described step C also comprises: to tennis racket gauge point mode of motion and the inertial parameter that obtains in described step B, by the Multisensor Data Fusion Algorithm of D-S evidence theory, obtain reflecting the consistent data of tennis racket motion feature.
6. a kind of tennis motion capture as claimed in claim 1 and analytic method, is characterized in that, described step D also comprises:
D1, gather various tennis racket motion sample pattern data, the sample pattern data of pre-collection are marked;
D2, go out to reflect one by one the proper vector of tennis racket motion essence feature from described sample pattern extracting data;
D3, divide according to described proper vector under category regions, make the proper vector that only comprises similar sample in each the different classes of zone after division, set up the sorter from proper vector to mapping relations affiliated classification;
D4, tennis pattern data to be detected are processed, extracted its proper vector;
D5, the proper vector of pattern data to be detected is input to described sorter, sorter is differentiated according to its proper vector, obtains the identification result to these pattern data to be detected, and identification result is carried out Action Semantic resolve.
7. a kind of tennis motion capture as claimed in claim 6 and analytic method, is characterized in that, described step D2 also comprises:
D21, described sample pattern data are carried out pre-service, obtain the tennis action data;
D22, extract the characteristic component of its essential characteristic of reflection from the tennis action data;
D23, described characteristic component is made up, obtain described proper vector.
8. a kind of tennis motion capture as claimed in claim 6 and analytic method, is characterized in that, described step D4 also comprises:
D41, described tennis pattern data to be identified are carried out pre-service, obtain Identification Data;
D42, extract the characteristic component of reflection Identification Data essential characteristic from Identification Data;
D43, described characteristic component is made up, obtain described proper vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105376286A CN103106411A (en) | 2012-12-13 | 2012-12-13 | Tennis motion capturing and analyzing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105376286A CN103106411A (en) | 2012-12-13 | 2012-12-13 | Tennis motion capturing and analyzing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103106411A true CN103106411A (en) | 2013-05-15 |
Family
ID=48314259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105376286A Pending CN103106411A (en) | 2012-12-13 | 2012-12-13 | Tennis motion capturing and analyzing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103106411A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016092454A1 (en) * | 2014-12-09 | 2016-06-16 | Basf Se | Optical detector |
| WO2017107318A1 (en) * | 2015-12-25 | 2017-06-29 | 深圳市酷浪云计算有限公司 | Ball motion tracker |
| CN107281709A (en) * | 2017-06-27 | 2017-10-24 | 深圳市酷浪云计算有限公司 | The extracting method and device, electronic equipment of a kind of sport video fragment |
| US9829564B2 (en) | 2013-06-13 | 2017-11-28 | Basf Se | Detector for optically detecting at least one longitudinal coordinate of one object by determining a number of illuminated pixels |
| CN107566911A (en) * | 2017-09-08 | 2018-01-09 | 广州华多网络科技有限公司 | A kind of live broadcasting method, device, system and electronic equipment |
| US9958535B2 (en) | 2013-08-19 | 2018-05-01 | Basf Se | Detector for determining a position of at least one object |
| US10012532B2 (en) | 2013-08-19 | 2018-07-03 | Basf Se | Optical detector |
| US10094927B2 (en) | 2014-09-29 | 2018-10-09 | Basf Se | Detector for optically determining a position of at least one object |
| US10120078B2 (en) | 2012-12-19 | 2018-11-06 | Basf Se | Detector having a transversal optical sensor and a longitudinal optical sensor |
| CN109528208A (en) * | 2018-11-08 | 2019-03-29 | 北京诺亦腾科技有限公司 | A kind of optics mixes motion capture system with inertia |
| CN110013658A (en) * | 2019-04-30 | 2019-07-16 | 西南大学 | A kind of dedicated tennis of tennis training pushes service control system and method |
| US10353049B2 (en) | 2013-06-13 | 2019-07-16 | Basf Se | Detector for optically detecting an orientation of at least one object |
| US10412283B2 (en) | 2015-09-14 | 2019-09-10 | Trinamix Gmbh | Dual aperture 3D camera and method using differing aperture areas |
| CN110960843A (en) * | 2019-12-23 | 2020-04-07 | 天水师范学院 | Basketball skill auxiliary training system |
| CN111375203A (en) * | 2020-04-22 | 2020-07-07 | 厦门鲸丽体育文化有限公司 | VR motion intelligent teaching athletic system |
| US10775505B2 (en) | 2015-01-30 | 2020-09-15 | Trinamix Gmbh | Detector for an optical detection of at least one object |
| US10890491B2 (en) | 2016-10-25 | 2021-01-12 | Trinamix Gmbh | Optical detector for an optical detection |
| US10948567B2 (en) | 2016-11-17 | 2021-03-16 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US10955936B2 (en) | 2015-07-17 | 2021-03-23 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US11041718B2 (en) | 2014-07-08 | 2021-06-22 | Basf Se | Detector for determining a position of at least one object |
| US11060922B2 (en) | 2017-04-20 | 2021-07-13 | Trinamix Gmbh | Optical detector |
| US11067692B2 (en) | 2017-06-26 | 2021-07-20 | Trinamix Gmbh | Detector for determining a position of at least one object |
| US11125880B2 (en) | 2014-12-09 | 2021-09-21 | Basf Se | Optical detector |
| US11211513B2 (en) | 2016-07-29 | 2021-12-28 | Trinamix Gmbh | Optical sensor and detector for an optical detection |
| US11428787B2 (en) | 2016-10-25 | 2022-08-30 | Trinamix Gmbh | Detector for an optical detection of at least one object |
| US11860292B2 (en) | 2016-11-17 | 2024-01-02 | Trinamix Gmbh | Detector and methods for authenticating at least one object |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243687A (en) * | 2011-04-22 | 2011-11-16 | 安徽寰智信息科技股份有限公司 | Physical education teaching auxiliary system based on motion identification technology and implementation method of physical education teaching auxiliary system |
-
2012
- 2012-12-13 CN CN2012105376286A patent/CN103106411A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243687A (en) * | 2011-04-22 | 2011-11-16 | 安徽寰智信息科技股份有限公司 | Physical education teaching auxiliary system based on motion identification technology and implementation method of physical education teaching auxiliary system |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10120078B2 (en) | 2012-12-19 | 2018-11-06 | Basf Se | Detector having a transversal optical sensor and a longitudinal optical sensor |
| US9829564B2 (en) | 2013-06-13 | 2017-11-28 | Basf Se | Detector for optically detecting at least one longitudinal coordinate of one object by determining a number of illuminated pixels |
| US9989623B2 (en) | 2013-06-13 | 2018-06-05 | Basf Se | Detector for determining a longitudinal coordinate of an object via an intensity distribution of illuminated pixels |
| US10845459B2 (en) | 2013-06-13 | 2020-11-24 | Basf Se | Detector for optically detecting at least one object |
| US10823818B2 (en) | 2013-06-13 | 2020-11-03 | Basf Se | Detector for optically detecting at least one object |
| US10353049B2 (en) | 2013-06-13 | 2019-07-16 | Basf Se | Detector for optically detecting an orientation of at least one object |
| US9958535B2 (en) | 2013-08-19 | 2018-05-01 | Basf Se | Detector for determining a position of at least one object |
| US10012532B2 (en) | 2013-08-19 | 2018-07-03 | Basf Se | Optical detector |
| US11041718B2 (en) | 2014-07-08 | 2021-06-22 | Basf Se | Detector for determining a position of at least one object |
| US10094927B2 (en) | 2014-09-29 | 2018-10-09 | Basf Se | Detector for optically determining a position of at least one object |
| WO2016092454A1 (en) * | 2014-12-09 | 2016-06-16 | Basf Se | Optical detector |
| US11125880B2 (en) | 2014-12-09 | 2021-09-21 | Basf Se | Optical detector |
| US10775505B2 (en) | 2015-01-30 | 2020-09-15 | Trinamix Gmbh | Detector for an optical detection of at least one object |
| US10955936B2 (en) | 2015-07-17 | 2021-03-23 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US10412283B2 (en) | 2015-09-14 | 2019-09-10 | Trinamix Gmbh | Dual aperture 3D camera and method using differing aperture areas |
| WO2017107318A1 (en) * | 2015-12-25 | 2017-06-29 | 深圳市酷浪云计算有限公司 | Ball motion tracker |
| US11211513B2 (en) | 2016-07-29 | 2021-12-28 | Trinamix Gmbh | Optical sensor and detector for an optical detection |
| US10890491B2 (en) | 2016-10-25 | 2021-01-12 | Trinamix Gmbh | Optical detector for an optical detection |
| US11428787B2 (en) | 2016-10-25 | 2022-08-30 | Trinamix Gmbh | Detector for an optical detection of at least one object |
| US10948567B2 (en) | 2016-11-17 | 2021-03-16 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US11635486B2 (en) | 2016-11-17 | 2023-04-25 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US11698435B2 (en) | 2016-11-17 | 2023-07-11 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US11860292B2 (en) | 2016-11-17 | 2024-01-02 | Trinamix Gmbh | Detector and methods for authenticating at least one object |
| US11415661B2 (en) | 2016-11-17 | 2022-08-16 | Trinamix Gmbh | Detector for optically detecting at least one object |
| US11060922B2 (en) | 2017-04-20 | 2021-07-13 | Trinamix Gmbh | Optical detector |
| US11067692B2 (en) | 2017-06-26 | 2021-07-20 | Trinamix Gmbh | Detector for determining a position of at least one object |
| CN107281709B (en) * | 2017-06-27 | 2019-04-05 | 深圳市酷浪云计算有限公司 | A kind of extracting method and device, electronic equipment of sport video segment |
| CN107281709A (en) * | 2017-06-27 | 2017-10-24 | 深圳市酷浪云计算有限公司 | The extracting method and device, electronic equipment of a kind of sport video fragment |
| CN107566911B (en) * | 2017-09-08 | 2021-06-29 | 广州方硅信息技术有限公司 | Live broadcast method, device and system and electronic equipment |
| CN107566911A (en) * | 2017-09-08 | 2018-01-09 | 广州华多网络科技有限公司 | A kind of live broadcasting method, device, system and electronic equipment |
| CN109528208A (en) * | 2018-11-08 | 2019-03-29 | 北京诺亦腾科技有限公司 | A kind of optics mixes motion capture system with inertia |
| CN110013658A (en) * | 2019-04-30 | 2019-07-16 | 西南大学 | A kind of dedicated tennis of tennis training pushes service control system and method |
| CN110960843A (en) * | 2019-12-23 | 2020-04-07 | 天水师范学院 | Basketball skill auxiliary training system |
| CN111375203A (en) * | 2020-04-22 | 2020-07-07 | 厦门鲸丽体育文化有限公司 | VR motion intelligent teaching athletic system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103106411A (en) | Tennis motion capturing and analyzing method | |
| Hu et al. | Joint monocular 3D vehicle detection and tracking | |
| CN102811343B (en) | Intelligent video monitoring system based on behavior recognition | |
| CN102243687A (en) | Physical education teaching auxiliary system based on motion identification technology and implementation method of physical education teaching auxiliary system | |
| CN110706259B (en) | Space constraint-based cross-shot tracking method and device for suspicious people | |
| KR101078975B1 (en) | Sensing device and method used to apparatus for virtual golf simulation | |
| CN105872477A (en) | Video monitoring method and system | |
| US20160042227A1 (en) | System and method for determining view invariant spatial-temporal descriptors for motion detection and analysis | |
| WO2014092552A2 (en) | Method for non-static foreground feature extraction and classification | |
| CN202662011U (en) | Physical education teaching auxiliary system based on motion identification technology | |
| CN103100205A (en) | Auxiliary device suitable for middle and primary school physical education evaluation and achieving method thereof | |
| CN113011310B (en) | Method and device for collecting shooting exercise amount, computer equipment and storage medium | |
| CN105069429A (en) | People flow analysis statistics method based on big data platform and people flow analysis statistics system based on big data platform | |
| CN112154482A (en) | Ball motion image analysis device and ball motion image analysis method | |
| CN103223236B (en) | Intelligent evaluation system for table tennis training machine | |
| CN107147920A (en) | A kind of multisource video clips played method and system | |
| CN101826155B (en) | Method for identifying act of shooting based on Haar characteristic and dynamic time sequence matching | |
| Ó Conaire et al. | Combining inertial and visual sensing for human action recognition in tennis | |
| CN103838258A (en) | Automatic tracking method and system applied to space-based space target | |
| Zhang et al. | Efficient golf ball detection and tracking based on convolutional neural networks and kalman filter | |
| Zhang et al. | Real-time golf ball detection and tracking based on convolutional neural networks | |
| Wang et al. | Basketball motion video target tracking algorithm based on improved gray neural network | |
| CN112861808B (en) | Dynamic gesture recognition method, device, computer equipment and readable storage medium | |
| US20230148135A1 (en) | Tracking user and object dynamics using a computerized device | |
| Bedico et al. | Gesture recognition of basketball referee violation signal by applying dynamic time warping algorithm using a wearable device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130515 |