Automatic Estimation of Football Possession via Improved YOLOv8 Detection and DBSCAN-Based Team Classification

TL;DR

This paper introduces a deep learning framework that automatically estimates football possession from broadcast videos using improved detection models and team classification, reducing the need for manual data.

Contribution

The novel framework combines enhanced YOLOv8 models and DBSCAN-based team classification to achieve accurate and efficient football possession estimation.

Findings

The framework achieved 79.4% and 71.1% validation average precision for ball and player detection, respectively.

It outperformed baseline models with an RMSE of 4.87 in possession estimation.

The system enables robust and label-free team assignment using jersey color features.

Abstract

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.

Figures