EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches

Guo Liang Goh iD, Guo Dong Goh iD, Jing Wen Pan iD, Phillis Soek Po Teng, Pui Wah Kong iD

Sensors · 11.12.2023 · 23 (24) · 9759

DOI: 10.3390/s23249759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.12.2023. Verfasst von Guo Liang Goh und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Badminton World Federation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In badminton, accurate service height detection is critical for ensuring fairness. We developed an automated service fault detection system that employed computer vision and machine learning, specifically utilizing the YOLOv5 object detection model. Comprising two cameras and a workstation, our system identifies elements, such as shuttlecocks, rackets, players, and players’ shoes. We developed an algorithm that can pinpoint the shuttlecock hitting event to capture its height information. To assess the accuracy of the new system, we benchmarked the results against a high sample-rate motion capture system and conducted a comparative analysis with eight human judges that used a fixed height service tool in a backhand low service situation. Our findings revealed a substantial enhancement in accuracy compared with human judgement; the system outperformed human judges by 3.5 times, achieving a 58% accuracy rate for detecting service heights between 1.150 and 1.155 m, as opposed to a 16% accuracy rate for humans. The system we have developed offers a highly reliable solution, substantially enhancing the consistency and accuracy of service judgement calls in badminton matches and ensuring fairness in the sport. The system’s development signifies a meaningful step towards leveraging technology for precision and integrity in sports officiation.

Schlagwörter

Stichwörter der Autor:innen

computer visionmachine learningrobot umpiresports technologysystem development

Autor:innen und Institutionen

  • School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, Singapore.
  • Physical Education and Sports Science Academic Group, National Institute of Education, Nanyang Technological University, 1 Nanyang Walk, Singapore 637616, Singapore.
  • Rehabilitation Research Institute of Singapore, Nanyang Technological University, 11 Mandalay Road, Singapore 308232, Singapore.

ORCID-Profile: Guo Liang Goh, Guo Dong Goh, Jing Wen Pan, Pui Wah Kong

Förderung

  • Badminton World Federation

Zitieren

APA

Goh, G. L., Goh, G. D., Pan, J. W., Teng, P. S. P., & Kong, P. W. (2023). Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches. Sensors, 23(24), 9759. https://doi.org/10.3390/s23249759

Vancouver

Goh GL, Goh GD, Pan JW, Teng PSP, Kong PW. Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches. Sensors. 2023;23(24):9759. doi:10.3390/s23249759

BibTeX
@article{Goh2023,
  author = {Goh, Guo Liang and Goh, Guo Dong and Pan, Jing Wen and Teng, Phillis Soek Po and Kong, Pui Wah},
  title = {Automated Service Height Fault Detection Using Computer Vision and Machine Learning for Badminton Matches},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {24},
  pages = {9759},
  doi = {10.3390/s23249759}
}
Kostenlos starten →