ORIGINAL RESEARCH article
Front. Sports Act. Living
Sec. Elite Sports and Performance Enhancement
Volume 7 - 2025 | doi: 10.3389/fspor.2025.1632326
This article is part of the Research TopicCombat Sports and Well-being: Prevention, Protection, and Development Across the Lifespan – Volume IIView all articles
Faster, more accurate? A feasibility study on replacing human judges with artificial intelligence in video review for the Paris Olympics Taekwondo competition
Provisionally accepted
- 1Yan'an University, Yan'an, China
- 2School of Business, Hong Kong Baptist University, Kowloon Tong, Hong Kong, SAR China
- 3School of Human Sciences, University of Western Australia, Perth, Western Australia, Australia
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 investigated the use of artificial intelligence (AI) to enhance the accuracy and efficiency of video reviews in Taekwondo. A total of 241 video review cases from the 2024 Paris Olympic Taekwondo competition were analyzed using ChatGPT-4.5 and OpenPose deep learning models. AI-generated penalty decisions were statistically compared to those made by international video review referees. AI-generated penalties showed strong agreement with those of international referees (Cohen's Kappa coefficient κ=0.897, p<0.001). Discrepancies were found in just 9 of the 241 cases, all involving head strikes, typically due to partial visual obstruction or minimal foot contact area. The AI system shortened review time by ~81% by rapidly identifying key frames, significantly improving review efficiency. However, human oversight remains essential for complex cases. A hybrid model -AI assisted pre-review followed by referee confirmation -is proposed to optimize both accuracy and efficiency. This approach could enhance fairness in World-class competitions and raise review standards in lower-tier events. Future research should expand the dataset, enable real-time penalty detection, and integrate multi-angle video and motion prediction to better capture subtle contact. The framework could also be adapted for other sports (e.g., baseball, basketball, boxing and judo).
Keywords: Taekwondo, artificial intelligence, Paris Olympics, Sports Referee, Sports Fairness
Received: 21 May 2025; Accepted: 07 Jul 2025.
Copyright: © 2025 ZHANG, Qu and Girard. 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: Yuncheng ZHANG, Yan'an University, Yan'an, 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.