Foul Detection for Table Tennis Serves Using Deep Learning
Electronics · 2024-12-25 · 14 (1) · 27
DOI: 10.3390/electronics14010027 ↗At a glance
Journal article in Electronics, published online on 2024-12-25. Written by Guang Liang Yang and 3 co-authors. Cited 6 times so far (Crossref); 21 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Detecting serve fouls in table tennis is critical for ensuring fair play. This paper explores the development of foul detection of table tennis serves by leveraging 3D ball trajectory analysis and deep learning techniques. Using a multi-camera setup and a custom dataset, we employed You Only Look Once (YOLO) models for ball detection and Transformers for critical trajectory point identification. We achieved 87.52% precision in detecting fast-moving balls and an F1 score of 0.93 in recognizing critical serve points such as the throw, highest, and hit points. These results enable precise serve segmentation and robust foul detection based on criteria like toss height and vertical angle compliance. The approach simplifies traditional methods by focusing solely on the ball motion, eliminating computationally intensive pose estimation. Despite limitations such as a controlled experimental environment, the findings demonstrate the feasibility of artificial intelligence (AI)-driven referee systems for table tennis games, providing a foundation for broader applications in sports officiating.
Cite
APA
Yang, G. L., Nguyen, M., Yan, W. Q., & Li, X. J. (2024). Foul Detection for Table Tennis Serves Using Deep Learning. Electronics, 14(1), 27. https://doi.org/10.3390/electronics14010027
Vancouver
Yang GL, Nguyen M, Yan WQ, Li XJ. Foul Detection for Table Tennis Serves Using Deep Learning. Electronics. 2024;14(1):27. doi:10.3390/electronics14010027
BibTeX
@article{Yang2024,
author = {Yang, Guang Liang and Nguyen, Minh and Yan, Wei Qi and Li, Xue Jun},
title = {Foul Detection for Table Tennis Serves Using Deep Learning},
journal = {Electronics},
year = {2024},
volume = {14},
number = {1},
pages = {27},
doi = {10.3390/electronics14010027}
}
EUVIMED