Automatic Estimation of Football Possession via Improved YOLOv8 Detection and DBSCAN-Based Team Classification
Sensors · 2026
DOI: 10.3390/s26041252 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Rong Guo und 10 weiteren Autor:innen. Beteiligte Einrichtung: College of Big Data, Yunnan Agricultural University, Kunming 650201, China. Hauptthemen laut MEDLINE: Football, Soccer. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Yunnan Province Basic Research Joint Project, the Undergraduate Education and Teaching Reform Research Projects of Yunnan Agricultural University.
Abstract (Originalsprache)
Recent developments in computer vision have significantly enhanced the automation and objectivity of sports analytics. This paper proposes a novel deep learning-based framework for estimating football possession directly from broadcast video, eliminating the reliance on manual annotations or event-based data that are often labor-intensive, subjective, and temporally coarse. The framework incorporates two structurally improved object detection models: YOLOv8-P2S3A for football detection and YOLOv8-HWD3A for player detection. These models demonstrate superior accuracy compared to baseline detectors, achieving 79.4% and 71.1% validation average precision, respectively, while maintaining low computational latency. Team identification is accomplished through unsupervised DBSCAN clustering on jersey color features, enabling robust and label-free team assignment across diverse match scenarios. Object trajectories are maintained via the Norfair multi-object tracking algorithm, and a temporally aware refinement module ensures accurate estimation of ball possession durations. Extensive experiments were conducted on a dataset comprising 20 full-match Video clips. The proposed system achieved a root mean square error (RMSE) of 4.87 in possession estimation, outperforming all evaluated baselines, including YOLOv10n (RMSE: 5.12) and YOLOv11 (RMSE: 5.17), with a substantial improvement over YOLOv6n (RMSE: 12.73). These results substantiate the effectiveness of the proposed framework in enhancing the precision, efficiency, and automation of football analytics, offering practical value for coaches, analysts, and sports scientists in professional settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Big Data, Yunnan Agricultural University, Kunming 650201, China.
- Center for Sports Intelligence Innovation and Application, Yunnan Agricultural University, Kunming 650201, China.
- College of Physical Education, Yunnan Agricultural University, Kunming 650201, China.
ORCID-Profile: Jianke Yang
Förderung
- the Yunnan Province Basic Research Joint Project
- the Undergraduate Education and Teaching Reform Research Projects of Yunnan Agricultural University
Zitieren
APA
Guo, R., Zeng, Y., Deng, R., Lei, Y., Che, Y., Yu, L., Zhang, J., Xu, X., Ma, Z., Zhang, J., & Yang, J. (2026). Automatic Estimation of Football Possession via Improved YOLOv8 Detection and DBSCAN-Based Team Classification. Sensors. https://doi.org/10.3390/s26041252
Vancouver
Guo R, Zeng Y, Deng R, Lei Y, Che Y, Yu L, et al. Automatic Estimation of Football Possession via Improved YOLOv8 Detection and DBSCAN-Based Team Classification. Sensors. 2026. doi:10.3390/s26041252
BibTeX
@article{Guo2026,
author = {Guo, Rong and Zeng, Yucheng and Deng, Rong and Lei, Yawen and Che, Yonglin and Yu, Lin and Zhang, Jianpeng and Xu, Xiaobin and Ma, Zhaoxiang and Zhang, Jiajin and Yang, Jianke},
title = {Automatic Estimation of Football Possession via Improved YOLOv8 Detection and DBSCAN-Based Team Classification},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26041252}
}
EUVIMED