Towards long-term player tracking with graph hierarchies and domain-specific features

TL;DR

This paper presents SportsSUSHI, a hierarchical graph-based method utilizing domain-specific features like jersey numbers and team IDs to improve long-term player tracking in team sports, demonstrated on SoccerNet and a new hockey dataset.

Contribution

Introduction of SportsSUSHI, a novel hierarchical graph approach that leverages domain-specific features for enhanced long-term player tracking in sports analytics.

Findings

SportsSUSHI outperforms existing methods on SoccerNet.

Inclusion of domain-specific features improves tracking accuracy.

The new hockey dataset enables evaluation of long-term tracking methods.

Abstract

In team sports analytics, long-term player tracking remains a challenging task due to player appearance similarity, occlusion, and dynamic motion patterns. Accurately re-identifying players and reconnecting tracklets after extended absences from the field of view or prolonged occlusions is crucial for robust analysis. We introduce SportsSUSHI, a hierarchical graph-based approach that leverages domain-specific features, including jersey numbers, team IDs, and field coordinates, to enhance tracking accuracy. SportsSUSHI achieves high performance on the SoccerNet dataset and a newly proposed hockey tracking dataset. Our hockey dataset, recorded using a stationary camera capturing the entire playing surface, contains long sequences and annotations for team IDs and jersey numbers, making it well-suited for evaluating long-term tracking capabilities. The inclusion of domain-specific features in our approach significantly improves association accuracy, as demonstrated in our experiments. The dataset and code are available at https://github.com/mkoshkina/sports-SUSHI.