AUTHOR=Zhang Yuncheng , Qu Ruojie , Girard Olivier 

TITLE=Faster, more accurate? A feasibility study on replacing human judges with artificial intelligence in video review for the Paris Olympics Taekwondo competition

JOURNAL=Frontiers in Sports and Active Living

VOLUME=Volume 7 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2025.1632326

DOI=10.3389/fspor.2025.1632326

ISSN=2624-9367

ABSTRACT=IntroductionThis study explores the potential of artificial intelligence (AI) to enhance the accuracy and efficiency of video review systems in Taekwondo, addressing limitations in current human-based judgment processes during competitions.MethodsA total of 241 video review cases from the 2024 Paris Olympic Taekwondo competition were analyzed. AI-based judgments were generated using ChatGPT-4.5 and OpenPose deep learning models. The AI-generated penalty decisions were statistically compared to those made by international video review referees using Cohen's Kappa coefficient.ResultsThe AI system demonstrated strong agreement with international referees (κ = 0.897, p < 0.001). Discrepancies occurred in only 9 out of 241 cases, primarily in scenarios involving head strikes with minimal contact or visual occlusion. Additionally, the AI system reduced average review time by approximately 81% by automatically identifying critical frames.DiscussionWhile AI significantly improved efficiency and showed high consistency with expert judgments, human oversight remains crucial for ambiguous or complex cases. A hybrid model—AI-assisted pre-review followed by referee confirmation—is proposed to optimize decision-making. Future developments should focus on real-time detection, multi-angle video integration, and application to other sports such as baseball, basketball, boxing, and judo.