Using Player's Body-Orientation to Model Pass Feasibility in Soccer
This work provides a domain-specific tool for soccer coaches and analysts to enhance game understanding and player decision-making, though it is incremental as it refines existing models with orientation features.
The paper tackles the problem of estimating the most feasible pass in soccer from monocular video by incorporating players' body orientation and opponents' spatial configuration, achieving over 0.7 Top-3 accuracy in analyzing over 6000 pass events.
Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's orientation (plus their location) and opponents' spatial configuration to compute the feasibility of pass events within players of the same team. Orientation data is gathered from body pose estimations that are properly projected onto the 2D game field; moreover, a geometrical solution is provided, through the definition of a feasibility measure, to determine which players are better oriented towards each other. Once analyzed more than 6000 pass events, results show that, by including orientation as a feasibility measure, a robust computational model can be built, reaching more than 0.7 Top-3 accuracy. Finally, the combination of the orientation feasibility measure with the recently introduced Expected Possession Value metric is studied; promising results are obtained, thus showing that existing models can be refined by using orientation as a key feature. These models could help both coaches and analysts to have a better understanding of the game and to improve the players' decision-making process.