Basketball motion analysis method based on 3D attitude estimation

A technique of attitude estimation and motion analysis, applied in the field of motion analysis, which can solve problems such as difficult player positioning

Pending Publication Date: 2020-09-29
NINGXIA UNIVERSITY
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] It is difficult for the traditional human body pose estimation algorithm to accurately locate the position of the players on the field during the game, especially in team sports, especially in basketball games where there are multiple people quickly crossing positions

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
  • Basketball motion analysis method based on 3D attitude estimation
  • Basketball motion analysis method based on 3D attitude estimation
  • Basketball motion analysis method based on 3D attitude estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] The goal of the invention in this context is to estimate 3D human pose, recognize human actions and track people from RGBD inputs from multiple cameras. Predict the coordinates of 3D key points of the human body by collecting depth images and color images. According to the key points and skeleton images of the human body as input, use spatiotemporal actions to identify human actions and generate action sequences; generate human body detection frames based on the coordinates of key points of the human body as tracking The input of the device, generate the trajectory sequence of the person, and analyze the trajectory of the person; such as figure 1 .

[0057] 1 Human Pose Estimation

[0058] The goal of the present invention is to estimate human body keypoints w=(w1,....wJ) from depth maps and color maps, J for keypoint coordinates in the real world. Without loss of generality, in the coordinate system defined by the present invention, the predictions of the present inv...

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 video analysis technology is more and more applied to basketball competitive sports, and can effectively help athletes or teams to improve competition results. The invention provides a basketballtraining auxiliary system method based on posture estimation and action recognition pair analysis. The system analyzes basketball games and training videos, coaches discover weaknesses in the games through analysis results of the system, the competitive level is improved, targeted preparation is conducted on the games in the future, team members and competition strategies are arranged according tothe characteristics of opponents, the analysis results are fed back to athletes, and the athletes are helped to reduce the risk of injury. The system adopts a multi-view three-dimensional attitude detection method, the 3D posture and position information of a player on a court are obtained through a plurality of video cameras containing depth information, the action of the player is recognized, player trajectory tracking is conducted, finally, the action of the player is predicted and analyzed, a player motion posture and trajectory model is constructed, and the system recognizes the motion posture on the court.

Description

technical field [0001] The invention relates to the technical field of motion analysis, in particular to a basketball motion analysis method based on 3D motion video analysis. Background technique [0002] In the era of big data, sports teams collect a lot of statistics about their players to make decisions to improve their team's performance; for example, hiring a new player or designing the best play for a particular game. In particular, in the field of basketball, a strong demand for player movement data analysis has emerged, from the initial manual annotation and analysis of videos to video analysis-based companies such as Second Spectrum and STATS through a set of ceiling cameras placed in the venue to extract information to reduce The workload of manual analysis. However, due to the many challenges in sports videos, such as multi-person occlusion, similar appearance or too fast and erratic motion, it is still an open research to automate the analysis of video sequence...

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): G06T7/246G06K9/00G06N3/04
CPCG06T7/246G06N3/049G06T2207/10016G06T2207/20016G06T2207/30196G06T2207/30241G06T2207/20081G06T2207/20084G06T2207/10028G06T2207/10024G06V40/23G06N3/045
Inventor 张鹏王红艳
Owner NINGXIA UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap