Key Frame Detection in Badminton Swings and Its Application to Physical Education

The use of video analysis in sports training has revolutionized the way coaches and players evaluate performance and develop strategies. This paper presents a machine learning based approach for key frame detection in badminton swings aimed at improving the learning experience for beginners through...

Full description

Saved in:
Bibliographic Details
Main Authors: Jen-Hao Hsu, Chi-Chuan Lee, Jing-Yuan Chang, Duan-Shin Lee
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11008633/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850123279940976640
author Jen-Hao Hsu
Chi-Chuan Lee
Jing-Yuan Chang
Duan-Shin Lee
author_facet Jen-Hao Hsu
Chi-Chuan Lee
Jing-Yuan Chang
Duan-Shin Lee
author_sort Jen-Hao Hsu
collection DOAJ
description The use of video analysis in sports training has revolutionized the way coaches and players evaluate performance and develop strategies. This paper presents a machine learning based approach for key frame detection in badminton swings aimed at improving the learning experience for beginners through visualization and real-time feedback. Our proposed method uses the MediaPipe framework to extract 3D coordinates of skeleton joints, which serve as input features for a machine learning based model that accurately predicts key frame positions in badminton swing videos. This model is integrated into a mobile app developed for Android tablets, allowing learners to record their swings and compare them with those of professional players, thereby enhancing badminton learning. Comparative studies show that models with graph convolutional networks, a prominent approach commonly used in skeleton-based human action recognition, outperform other existing methods in terms of accuracy and reliability. Experimental studies demonstrate the app’s positive impact on performance, motivation, and self-perception. One main contribution of this research is the development of a robust key frame detection model. Another main contribution is that we implement this key frame detection model in a tablet and verify it through extensive experiments.
format Article
id doaj-art-581aae71634d46dc87ca648dad1545bb
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-581aae71634d46dc87ca648dad1545bb2025-08-20T02:34:38ZengIEEEIEEE Access2169-35362025-01-0113912489126210.1109/ACCESS.2025.357210511008633Key Frame Detection in Badminton Swings and Its Application to Physical EducationJen-Hao Hsu0https://orcid.org/0000-0002-4868-9324Chi-Chuan Lee1https://orcid.org/0009-0007-5511-6464Jing-Yuan Chang2https://orcid.org/0009-0007-3986-5510Duan-Shin Lee3https://orcid.org/0000-0003-4578-2002Physical Education Office, National Tsing Hua University, Hsinchu, TaiwanInstitute of Communications Engineering, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanThe use of video analysis in sports training has revolutionized the way coaches and players evaluate performance and develop strategies. This paper presents a machine learning based approach for key frame detection in badminton swings aimed at improving the learning experience for beginners through visualization and real-time feedback. Our proposed method uses the MediaPipe framework to extract 3D coordinates of skeleton joints, which serve as input features for a machine learning based model that accurately predicts key frame positions in badminton swing videos. This model is integrated into a mobile app developed for Android tablets, allowing learners to record their swings and compare them with those of professional players, thereby enhancing badminton learning. Comparative studies show that models with graph convolutional networks, a prominent approach commonly used in skeleton-based human action recognition, outperform other existing methods in terms of accuracy and reliability. Experimental studies demonstrate the app’s positive impact on performance, motivation, and self-perception. One main contribution of this research is the development of a robust key frame detection model. Another main contribution is that we implement this key frame detection model in a tablet and verify it through extensive experiments.https://ieeexplore.ieee.org/document/11008633/Badmintonkey frame detectionsports education technologycomputer visiongraph convolution networkmulti-layer perceptron
spellingShingle Jen-Hao Hsu
Chi-Chuan Lee
Jing-Yuan Chang
Duan-Shin Lee
Key Frame Detection in Badminton Swings and Its Application to Physical Education
IEEE Access
Badminton
key frame detection
sports education technology
computer vision
graph convolution network
multi-layer perceptron
title Key Frame Detection in Badminton Swings and Its Application to Physical Education
title_full Key Frame Detection in Badminton Swings and Its Application to Physical Education
title_fullStr Key Frame Detection in Badminton Swings and Its Application to Physical Education
title_full_unstemmed Key Frame Detection in Badminton Swings and Its Application to Physical Education
title_short Key Frame Detection in Badminton Swings and Its Application to Physical Education
title_sort key frame detection in badminton swings and its application to physical education
topic Badminton
key frame detection
sports education technology
computer vision
graph convolution network
multi-layer perceptron
url https://ieeexplore.ieee.org/document/11008633/
work_keys_str_mv AT jenhaohsu keyframedetectioninbadmintonswingsanditsapplicationtophysicaleducation
AT chichuanlee keyframedetectioninbadmintonswingsanditsapplicationtophysicaleducation
AT jingyuanchang keyframedetectioninbadmintonswingsanditsapplicationtophysicaleducation
AT duanshinlee keyframedetectioninbadmintonswingsanditsapplicationtophysicaleducation