Techniques for human motion analysis and classification in intelligent sports training

Ge Dan

doi:10.1117/12.3031397

19 July 2024 Techniques for human motion analysis and classification in intelligent sports training

Ge Dan

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 1318186 (2024) https://doi.org/10.1117/12.3031397
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

This paper explores the application of Convolutional Neural Networks (CNNs) in the classification of human body movements specific to sports training. Utilizing a dataset comprising images of four fundamental sports movements - jumping, running, weightlifting, and swimming - the study demonstrates the implementation of a CNN model to accurately identify and categorize these movements. The model achieved a notable classification accuracy of 95%, showcasing the efficacy of deep learning techniques in the nuanced field of sports motion analysis. This research highlights the potential of machine learning in enhancing the precision of movement classification, which is crucial in developing advanced training methods and injury prevention strategies in sports. While the results are promising, they also reveal areas for further improvement, particularly in distinguishing between closely related movement types. The findings of this study are significant for the advancement of intelligent sports training systems, offering insights into the integration of technology in sports science.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ge Dan "Techniques for human motion analysis and classification in intelligent sports training", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 1318186 (19 July 2024); https://doi.org/10.1117/12.3031397

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available