Publication

FootBots: A transformer-based architecture for motion prediction in soccer

Conference Article

Conference

IEEE International Conference on Image Processing (ICIP)

Edition

2024

Pages

2313-2319

Doc link

http://dx.doi.org/10.1109/ICIP51287.2024.10647396

File

Download the digital copy of the doc pdf document

Abstract

Motion prediction in soccer involves capturing complex dynamics from player and ball interactions. We present FootBots, an encoder-decoder transformer-based architecture addressing motion prediction and conditioned motion prediction through equivariance properties. FootBots captures temporal and social dynamics using set attention blocks and multi-attention block decoder. Our evaluation utilizes two datasets: a real soccer dataset and a tailored synthetic one. Insights from the synthetic dataset highlight the effectiveness of FootBots' social attention mechanism and the significance of conditioned motion prediction. Empirical results on real soccer data demonstrate that FootBots outperforms baselines in motion prediction and excels in conditioned tasks, such as predicting the players based on the ball position, predicting the offensive (defensive) team based on the ball and the defensive (offensive) team, and predicting the ball position based on all players. Our evaluation connects quantitative and qualitative findings.

Categories

computer vision.

Author keywords

Motion prediction, Signal forecasting, Transformer, Trajectory understanding, Soccer.

Scientific reference

G. Capellera, L. Ferraz, A. Rubio, A. Agudo and F. Moreno-Noguer. FootBots: A transformer-based architecture for motion prediction in soccer, 2024 IEEE International Conference on Image Processing, 2024, Abu Dhabi, UAE, pp. 2313-2319.