Spiideo SoccerNet SynLoc: Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data

Håkan Ardö, Mikael Nilsson, Anthony Cioppa, Floriane Magera, Silvio Giancola, Haochen Liu, Bernard Ghanem, Marc Van Droogenbroeck

2025

Abstract

Currently, most research and public datasets for video sports analytics are base on detecting players as bounding boxes in broadcast videos. Going from there to precise locations on the pitch is however hard. Modern solutions are making dedicated static cameras covering the entire pitch more readily accessible, and they are now used more and more even in lower tiers. To promote research that can take benefits of such cameras and produce more precise pitch locations, we introduce the Spiideo SoccerNet SynLoc dataset. It consists of synthetic athletes rendered on top of images from real world installation of such cameras. We also introduce a new task of detecting the players in the world pitch coordinate system and a new metric based solely on real world physical properties where the representation in the image is irrelevant. The dataset and code are publicly available at https://github.com/Spiideo/sskit.

Paper Citation

in Harvard Style

Ardö H., Nilsson M., Cioppa A., Magera F., Giancola S., Liu H., Ghanem B. and Van Droogenbroeck M. (2025). Spiideo SoccerNet SynLoc: Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 278-285. DOI: 10.5220/0013108200003912

in Bibtex Style

@conference{visapp25,
author={Håkan Ardö and Mikael Nilsson and Anthony Cioppa and Floriane Magera and Silvio Giancola and Haochen Liu and Bernard Ghanem and Marc Van Droogenbroeck},
title={Spiideo SoccerNet SynLoc: Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={278-285},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013108200003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Spiideo SoccerNet SynLoc: Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data
SN - 978-989-758-728-3
AU - Ardö H.
AU - Nilsson M.
AU - Cioppa A.
AU - Magera F.
AU - Giancola S.
AU - Liu H.
AU - Ghanem B.
AU - Van Droogenbroeck M.
PY - 2025
SP - 278
EP - 285
DO - 10.5220/0013108200003912
PB - SciTePress