Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Table tennis action recognition method and system based on posture segmentation and key point features

An action recognition and key point technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of complex production, difficult to popularize, and high cost of intelligent equipment, and achieve the effect of improving accuracy and simple hardware equipment.

Active Publication Date: 2019-11-19
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional method is time-consuming and labor-intensive, and the cost of smart devices is high and the production is complicated and difficult to popularize.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Table tennis action recognition method and system based on posture segmentation and key point features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0044] A kind of table tennis action recognition method based on gesture segmentation and key point features of the present invention, see figure 1 shown, including the following steps:

[0045] Step 1, obtain and shoot the video of the table tennis player receiving and serving action during training;

[0046] A web camera is placed in front of the athlete to shoot the table tennis player's serve-receiving action during training, and the video of the table tennis player's serve-receiving action during training is obtained from the web camera.

[0047] Step 2, segment the video frame image that only includes the arm region from the video;

[0048] Since the action category of the table tennis ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a table tennis action recognition method and system based on posture segmentation and key point features. The method comprises the following steps: obtaining a video of shooting a ball receiving and serving action of a table tennis player during training; segmenting a video frame image only containing the arm region from the video; skeleton joint point estimation of the armarea is carried out on the video frame images only containing the arm area, and acquiring arm skeleton key point information in each video frame image; according to the skeleton key point informationin each video frame image, obtaining spatial structure features and time sequence features of skeleton key points in each frame; recognizing and classifying the ball receiving and serving actions ofthe athlete according to the spatial structure characteristics and the time sequence characteristics of the skeleton key points. According to the method, the spatial-temporal relationship of the ballreceiving and serving actions is analyzed, the spatial-temporal characteristics are established, and the action recognition accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of image and video analysis, in particular to a method and system for recognizing table tennis receiving and serving actions based on human body posture segmentation combined with skeleton key point features. Background technique [0002] With the acceleration of the informationization process and the continuous development of artificial intelligence technology, sports as an integral part of social activities, the application of artificial intelligence will greatly affect the traditional organizational forms of sports training, competition, and competitive sports management. The traditional table tennis return training is mainly guided by the coaches. With the development of technology, sports equipment embedded with smart devices has gradually appeared, which is used to collect data such as sports information and human body indicators, and store and analyze the data through the network. It is used to guide ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/62
CPCG06V40/28G06V10/267G06F18/241
Inventor 李晓飞黄尔俊丁朔
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com