A spatio-temporal graph-based model for team sports analysis

Abstract

Team sports represent complex phenomena characterized by both spatial and temporal dimensions, making their analysis inherently challenging. In this study, we examine team sports as complex systems, specifically focusing on the tactical aspects influenced by external constraints. To this end, we introduce a new generic graph-based model to analyze these phenomena. Specifically, we model a team sport's attacking play as a directed path containing absolute and relative ball carrier-centered spatial information, temporal information, and semantic information. We apply our model to union rugby, aiming to validate two hypotheses regarding the impact of the pedagogy provided by the coach on the one hand, and the effect of the initial positioning of the defensive team on the other hand. Preliminary results from data collected on six-player rugby from several French clubs indicate notable effects of these constraints. The model is intended to be applied to other team sports and to validate additional hypotheses related to team coordination patterns, including upcoming applications in basketball.

Figures (12)

• Figure 1: Example of the skeleton graph for $n=3$, $m_\textup{rel} = 2$, $m_\textup{abs} = 2$, and two results vertices. For more readability, we omit the labels. Edges in $E_\text{sp-th}$ for spatial and/or thematic relations are in thick orange, and we specify edges for which there are only thematic labels in dashed thick orange. Edges in $E_\text{res}$ for result relations are in thin black.
• Figure 2: Example of a path on a skeleton graph.
• Figure 3: Absolute zones (on the left) and relative zones (on the right) for rugby.
• Figure 4: Example of a spatial position at a given instant time, with the 6 players (blue dots) and among them the ball carrier (circled in orange). The spatial information related to this position is ($(2,3)$, Middle).
• Figure 5: Tree of thematic labels in rugby.