Real-time Localization of a Soccer Ball from a Single Camera

TL;DR

This paper presents a fast, accurate, and computationally efficient method for real-time 3D soccer ball tracking from a single camera, suitable for live broadcasts and challenging visual conditions.

Contribution

It introduces a multi-mode state model that accelerates optimization while maintaining centimeter-level accuracy, enabling single-camera 3D ball tracking in real-time.

Findings

Achieves real-time 3D ball localization on standard CPUs.

Performs comparably to multi-camera systems in accuracy.

Effective even under occlusion, motion blur, and complex backgrounds.

Abstract

We propose a computationally efficient method for real-time three-dimensional football trajectory reconstruction from a single broadcast camera. In contrast to previous work, our approach introduces a multi-mode state model with $W$ discrete modes to significantly accelerate optimization while preserving centimeter-level accuracy -- even in cases of severe occlusion, motion blur, and complex backgrounds. The system operates on standard CPUs and achieves low latency suitable for live broadcast settings. Extensive evaluation on a proprietary dataset of 6K-resolution Russian Premier League matches demonstrates performance comparable to multi-camera systems, without the need for specialized or costly infrastructure. This work provides a practical method for accessible and accurate 3D ball tracking in professional football environments.