Vision-based human movement matching for Muay Thai training support system

Name: Somkiat Wangsiripitak

Organization : King Mongkut’s Institute of Technology Ladkrabang. School of Information Technology

Email : somkiat@it.kmitl.ac.th

Name: Nawin Wedsuwan

Organization : King Mongkut’s Institute of Technology Ladkrabang. School of Information Technology

Email : 63070232@kmitl.ac.th

Name: Napong Pipatbowornkul

Organization : King Mongkut’s Institute of Technology Ladkrabang. School of Information Technology

Email : 63070219@kmitl.ac.th

Name: Bhattarabhorn Wattanacheep

Organization : King Mongkut’s Institute of Technology Ladkrabang. School of Information Technology

Email : bhattarabhorn@it.kmitl.ac.th

LCSH: Muay Thai -- Data processing

LCSH: Martial arts -- Data processing

LCSH: Deep learning (Machine learning)

Abstract: An algorithm is proposed to evaluate Muay Thai trainees based on body movement matching with a trainer, aiming to support Muay Thai training. Skeletons of the trainee in image sequences captured by a monocular camera are extracted using a pre-trained deep learning model. They are then synchronized with those of the trainer by matching keyframes and subsequently matching other image frames between both sequences using dynamic time warping. In each matched frame, the skeleton lines, or bones, are compared by measuring the angle deviation of each bone from the trainee to the corresponding bone of the trainer. The similarity score of each bone pair is computed based on a cosine similarity metric. Simultaneously, a predefined upper-value limit of the maximum expected difference in bone comparison is applied to enhance the difference in similarity scores between excellent and underperformed postures, making the evaluation results more distinctive. Each matched frame is then scored by weighted averaging of bone scores, allowing the evaluation to focus adaptively on significant parts of the body according to movement types. The overall score of the sequence is an average over all frames. Experimental results demonstrate that the proposed scoring method is flexible for use with an off-the-shelf camera and adaptive to a marking scheme that often changes with training strategies and patterns. Prior matching of keyframes reduces mismatching of similar but non-corresponding frames. The score is also normalized to penalize misoriented bones, resulting in even lower scores for trainees with less skill

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2024

Modified: 2026-06-02

Issued: 2026-06-02

บทความ/Article

application/pdf

BibliograpyCitation : In Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI) Association, Thailand. 2024 21th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON 2024) (pp.187-192). Piscataway, NJ : IEEE

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	ECTI-CON 2024pp.187-192.pdf	718.29 KB

ใช้เวลา

0.033025 วินาที