PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectories

2026-02-12

AI Summary

This work proposes a method for automatically detecting ball possession events in soccer matches using only player trajectories, addressing the high cost of manual annotation and the reliance on expensive equipment for ball tracking. Players are modeled as a dynamic fully connected graph, and a Set Attention network is employed to compute edge-wise emission and transition scores. A conditional random field (CRF) enforces the constraint that exactly one edge per frame represents the ball possession state, ensuring temporal consistency. The optimal possession sequence is then obtained via Viterbi decoding. To the best of our knowledge, this is the first end-to-end approach capable of inferring ball possession without explicit ball trajectory data. The method significantly reduces dependence on manual labeling and costly tracking systems while maintaining high accuracy, thereby facilitating downstream analytical tasks.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Despite recent advances in AI, event data collection in soccer still relies heavily on labor-intensive manual annotation. Although prior work has explored automatic event detection using player and ball trajectories, ball tracking also remains difficult to scale due to high infrastructural and operational costs. As a result, comprehensive data collection in soccer is largely confined to top-tier competitions, limiting the broader adoption of data-driven analysis in this domain. To address this challenge, this paper proposes PathCRF, a framework for detecting on-ball soccer events using only player tracking data. We model player trajectories as a fully connected dynamic graph and formulate event detection as the problem of selecting exactly one edge corresponding to the current possession state at each time step. To ensure logical consistency of the resulting edge sequence, we employ a Conditional Random Field (CRF) that forbids impossible transitions between consecutive edges. Both emission and transition scores dynamically computed from edge embeddings produced by a Set Attention-based backbone architecture. During inference, the most probable edge sequence is obtained via Viterbi decoding, and events such as ball controls or passes are detected whenever the selected edge changes between adjacent time steps. Experiments show that PathCRF produces accurate, logically consistent possession paths, enabling reliable downstream analyses while substantially reducing the need for manual event annotation. The source code is available at https://github.com/hyunsungkim-ds/pathcrf.git.

Problem

• soccer event detection
• player trajectories
• ball tracking
• manual annotation
• data-driven analysis

Innovation

• PathCRF
• ball-free event detection
• player trajectory
• Conditional Random Field
• possession inference