VIDEO SKELETONIZATION AND AI: A NOVEL APPROACH FOR ANALYZING KINEMATICS IN TABLE TENNIS

Authors

Enrico Ferlinghetti, Università degli studi di BresciaFollow
Nicola Abeni, Università degli studi di BresciaFollow
Ryushi Kumamoto, Kyushu UniversityFollow
Ping Yeap LOH, Kyushu UniversityFollow
Matteo Lancini, University of Brescia, ItalyFollow

Category

Sports Performance & Elite Sports

Document Type

Paper

Abstract

This study introduces a simple yet effective system to measure table tennis player movements and relate them to the moment the ball hits the racket. The system accurately measures shoulder, elbow, hip and knee joint angles without hindering player movements, using only two GoPro Hero 10 cameras and the Mediapipe framework. Ten male participants were evaluated using synchronized cameras and a custom-trained YOLOv8 algorithm to pinpoint the moment of impact between the racket and the ball. This approach, avoiding participant-worn equipment, offers a streamlined solution for assessing table tennis movements, promising potential applications in sports analysis.

Recommended Citation

Ferlinghetti, Enrico; Abeni, Nicola; Kumamoto, Ryushi; LOH, Ping Yeap; and Lancini, Matteo (2024) "VIDEO SKELETONIZATION AND AI: A NOVEL APPROACH FOR ANALYZING KINEMATICS IN TABLE TENNIS," ISBS Proceedings Archive: Vol. 42: Iss. 1, Article 219.
Available at: https://commons.nmu.edu/isbs/vol42/iss1/219