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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vorobev, Dmitrii, Prosvetov, Artem, Daou, Karim Elhadji
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916785820794880
author Vorobev, Dmitrii
Prosvetov, Artem
Daou, Karim Elhadji
author_facet Vorobev, Dmitrii
Prosvetov, Artem
Daou, Karim Elhadji
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-time Localization of a Soccer Ball from a Single Camera
Vorobev, Dmitrii
Prosvetov, Artem
Daou, Karim Elhadji
Computer Vision and Pattern Recognition
Machine Learning
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.
title Real-time Localization of a Soccer Ball from a Single Camera
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.07981