AI-Powered Precision in Sport Taekwondo: Enhancing Fairness, Speed, and Trust in Competition (FST.ai)

2025-07-19

AI Summary

Traditional taekwondo judging suffers from high latency, strong subjectivity, and poor inter-rater consistency, undermining competition fairness and athlete trust. To address this, we propose FST.ai—a novel framework that integrates real-time pose estimation, temporal action classification, and impact biomechanics analysis to enable millisecond-level automatic detection and scoring of head kicks. FST.ai is the first system to jointly model kinematic and kinetic features for combat-sport judging. It exhibits cross-disciplinary generalizability to other striking sports (e.g., sanshou, karate) and supports efficient edge-device deployment. Evaluated on official taekwondo competitions, FST.ai achieves an average adjudication latency of ≤1.2 seconds (reduced from minutes) and 94.7% scoring accuracy. Experimental results demonstrate substantial improvements in judging consistency (Cohen’s κ = 0.91) and decision transparency. This work establishes a scalable, physics-informed paradigm for intelligent officiating in combat sports.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The integration of Artificial Intelligence (AI) into sports officiating represents a paradigm shift in how decisions are made in competitive environments. Traditional manual systems, even when supported by Instant Video Replay (IVR), often suffer from latency, subjectivity, and inconsistent enforcement, undermining fairness and athlete trust. This paper introduces FST.ai, a novel AI-powered framework designed to enhance officiating in Sport Taekwondo, particularly focusing on the complex task of real-time head kick detection and scoring. Leveraging computer vision, deep learning, and edge inference, the system automates the identification and classification of key actions, significantly reducing decision time from minutes to seconds while improving consistency and transparency. Importantly, the methodology is not limited to Taekwondo. The underlying framework -- based on pose estimation, motion classification, and impact analysis -- can be adapted to a wide range of sports requiring action detection, such as judo, karate, fencing, or even team sports like football and basketball, where foul recognition or performance tracking is critical. By addressing one of Taekwondo's most challenging scenarios -- head kick scoring -- we demonstrate the robustness, scalability, and sport-agnostic potential of FST.ai to transform officiating standards across multiple disciplines.

Problem

• Enhancing fairness and speed in Taekwondo officiating using AI
• Reducing latency and subjectivity in real-time head kick detection
• Adapting AI framework for multiple sports action detection

Innovation

• AI-powered real-time head kick detection
• Computer vision and deep learning integration
• Edge inference for fast decision-making