EUVIMEDEUVIMED entdecken
Crossref

YOLO-Ball: Real-time tennis ball detection under occlusion and motion blur

Yongjun Ding, Ziwen Fan, Yilong Zhao

Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology · 02.03.2026

DOI: 10.1177/17543371261423768 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology, online erschienen am 02.03.2026. Verfasst von Yongjun Ding und 2 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Sichuan Sports Science Society.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes YOLO-Ball, an improved real-time detection model addressing tennis ball detection challenges including small target size, motion blur, and player/racket occlusion. The main contributions include: (1) A multi-branch occlusion-aware attention mechanism for dynamic multi-scale feature fusion, (2) A dual-flow shallow fusion pyramid combining P2 features with bidirectional fusion to enhance small target and blur handling, and (3) A dynamic balance loss integrating Normalized Gaussian Wasserstein Distance (NWD) and Intersection over Union (IoU) with learnable alignment weights. Experiments on the constructed tennis dataset show 82.2% precision and a mean Average Precision at an Intersection over Union threshold of 0.5 (mAP@0.5) of 70.9%, outperforming YOLOv8/v10/v11 by up to 12.5%. YOLO-Ball also demonstrates generalization for volleyball and football detection, thereby providing a robust detection framework for scenarios involving high-speed, small targets.

Förderung

  • Sichuan Sports Science Society

Zitieren

APA

Ding, Y., Fan, Z., & Zhao, Y. (2026). YOLO-Ball: Real-time tennis ball detection under occlusion and motion blur. Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology. https://doi.org/10.1177/17543371261423768

Vancouver

Ding Y, Fan Z, Zhao Y. YOLO-Ball: Real-time tennis ball detection under occlusion and motion blur. Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology. 2026. doi:10.1177/17543371261423768

BibTeX
@article{Ding2026,
  author = {Ding, Yongjun and Fan, Ziwen and Zhao, Yilong},
  title = {YOLO-Ball: Real-time tennis ball detection under occlusion and motion blur},
  journal = {Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology},
  year = {2026},
  doi = {10.1177/17543371261423768}
}
Kostenlos starten →