article · Journal of Human Sport and Exercise
Integrating artificial intelligence into sports technical analysis offers ways to enhance athletic tactics and performance. Conventional approaches to tactical analysis in competitive sports often suffer from delays, high costs, data loss, and limited accuracy. Using convolutional neural networks and graph convolution models enables the automated analysis of karate athletes by tracking movement trajectories, recognising technical actions, and gathering action frequency statistics. In addition, eye-tracking tools and facial biometric analysis from video recordings can capture visual strategies and measure skill-specific performance criteria. These measurements support the creation of objective scoring rubrics to evaluate athletes. By comparing these scores across competitors, coaches and athletes can identify strengths and weaknesses to optimise training regimens, technique, and decision-making during kumite matches.
Fast-paced combat sports like karate demand rapid decision-making and precise technique. Traditional performance reviews often rely on subjective, delayed, or costly observation. Applying artificial intelligence and computer vision to measure facial biometrics and visual tracking provides objective feedback. This helps athletes and coaches understand visual focus, identify tactical flaws, and refine training strategies more effectively.
The research points towards sports analytics software and automated coaching tools for martial arts organisations, trainers, and athletes. By combining video analysis with neural networks, the approach could power objective performance evaluation platforms. Based on the abstract, the work appears to be at an early, exploratory stage, focusing on exhibition performances to establish measurement rubrics rather than presenting a finished commercial product.
AI-generated from the published abstract. Always read the original work before citing.
The document discusses the use of facial fingerprint analysis using artificial intelligence (AI) techniques to quickly respond during karate matches. The integration of AI with sports technical analysis has the potential to improve the technical and tactical level of athletes. Traditional methods for tactical intelligence analysis in competitive sports have limitations such as high cost, data loss, delay, and low accuracy, but the use of convolutional neural networks and graph convolution models has shown promising results in the automatic, intelligent analysis of karate athletes' technical action recognition, action frequency statistics, and trajectory tracking. Eye-tracking technology is also used to analyse various aspects of performance and help identify visual strategies employed by athletes. By analysing video footage of facial biometrics during karate competition performances, performance criteria can be measured based on relevant skills in karate, and an objective scoring rubric can be developed for each criterion. Then, the scores can be compared between performers to see individual strengths and weaknesses and to optimize training, technique, and performance. Ultimately, the study seeks to investigate how to improve performance and decision-making in kumite by using AI techniques to analyse the eye print during an exhibition performance.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.55860/r05vhj78
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
