EFPI: Elastic Formation and Position Identification in Football (Soccer) using Template Matching and Linear Assignment

2025-06-30

AI Summary

In football tactical analysis, robust formation identification and accurate player-to-position assignment from spatiotemporal tracking data remain challenging. This paper proposes EFPI (Elastic Formation Pattern Identification), a novel framework that combines template matching—via scale-invariant alignment and Euclidean distance minimization—with linear assignment to solve player-position mapping. To suppress short-term formation jitter, EFPI introduces a temporal stability constraint, enabling multi-granularity analysis at the frame, possession-sequence, and full-match levels. Compared to static matching approaches, EFPI maintains high accuracy while significantly improving the reasonableness and robustness of formation-state transition detection. The method is open-sourced and integrated into the *unravelsports* Python package, providing a reproducible, easy-to-deploy, standardized module for empirical tactical research.

Technology Category

• Computer Vision: Motion & Tracking
• Humans and AI: Teamwork, Team formation
• Machine Learning: Feature Construction/Reformulation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

Understanding team formations and player positioning is crucial for tactical analysis in football (soccer). This paper presents a flexible method for formation recognition and player position assignment in football using predefined static formation templates and cost minimization from spatiotemporal tracking data, called EFPI. Our approach employs linear sum assignment to optimally match players to positions within a set of template formations by minimizing the total distance between actual player locations and template positions, subsequently selecting the formation with the lowest assignment cost. To improve accuracy, we scale actual player positions to match the dimensions of these formation templates in both width and length. While the method functions effectively on individual frames, it extends naturally to larger game segments such as complete periods, possession sequences or specific intervals (e.g. 10 second intervals, 5 minute intervals etc.). Additionally, we incorporate an optional stability parameter that prevents unnecessary formation changes when assignment costs differ only marginally between time segments. EFPI is available as open-source code through the unravelsports Python package.

Problem

• Identify football team formations using template matching
• Assign player positions via cost minimization from tracking data
• Improve accuracy by scaling player positions to template dimensions

Innovation

• Uses template matching for formation recognition
• Applies linear assignment for player positioning
• Scales player positions to template dimensions