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

INTRODUCTION

This 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.

METHODS

A 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.

RESULTS

The AI system demonstrated strong agreement with international referees ( = 0.897,  < 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.

DISCUSSION

While 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.