ORIGINAL RESEARCH article
Front. Sports Act. Living
Sec. Biomechanics and Control of Human Movement
Volume 7 - 2025 | doi: 10.3389/fspor.2025.1635581
This article is part of the Research TopicRevolutionizing sports science: Biomechanical models, wearable tech, and AIView all 3 articles
Development of a MediaPipe-Based Framework for Biomechanical Quantification of Table Tennis Forehand Strokes
Provisionally accepted
- Nanjing Sport Institute, Nanjing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
This study developed a MediaPipe-based framework for kinematic analysis of table tennis forehand strokes using a single-camera system. We analyzed 34 female players (aged 9.1-21.7 years) from provincial teams, recording a total of 340 strokes (10 per player). An SVM model was used to predict ball speed, after which 320 strokes (8-10 per player) were retained by removing outliers in ball speed. From MediaPipe Pose data, we extracted kinematic parameters across three levels: (1) Landmark parameters including positional range (PR), mean velocity (MV), peak velocity (PV), and impact velocity (IV), decomposed into resultant components (subscript R) and axial components (subscripts x, y, z); (2) Segment parameters including angular range (AR), mean angular velocity (MAV), peak angular velocity (PAV), and impact angular velocity (IAV), analyzed as resultant components (subscript R) and planar components (subscripts xy, yz, zx);(3) Joint parameters including joint angular range (JAR), joint mean angular velocity (JMAV), joint peak angular velocity (JPAV), and joint impact angular velocity (JIAV), treated as scalar quantities without directional decomposition. Within-subject correlation coefficients (r ws ) were calculated using fastest and slowest strokes per player to identify key biomechanical parameters. Resultsshowed ball speed increased with greater playing-side arm linear movement at the shoulder, elbow and wrist , as well as with enhanced rotational motion at the playing-side upper arm, shoulder line , and hip line. Conversely, ball speed decreased with excessive contralateral shoulder horizontal flexion/extension and playing-side elbow flexion-extension. Between-subject correlation coefficients (r_bs ) revealed that forehand speed increases with age and height before 14.3 years (r_bs = 0.68) but plateaus thereafter (r_bs = 0.17). This MediaPipe-based framework demonstrates potential for efficient biomechanical analysis in table tennis, providing a promising foundation for lightweight real-time analysis solutions.
Keywords: Motion analysis, mediapipe, table tennis, Forehand stroke, Biomechanics
Received: 26 May 2025; Accepted: 28 Jul 2025.
Copyright: © 2025 Lyu, Duan, Yang and Ye. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Yuanyuan Lyu, Nanjing Sport Institute, Nanjing, China
Qiang Ye, Nanjing Sport Institute, Nanjing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.