SoccerTrack v2: A Full-Pitch Multi-View Soccer Dataset for Game State Reconstruction
This dataset addresses a problem for researchers in computer vision and soccer analytics by providing a new benchmark, though it is incremental as it builds on prior datasets with broader coverage.
The authors tackled the lack of comprehensive datasets for soccer analytics by introducing SoccerTrack v2, a public dataset with 10 full-length, panoramic 4K recordings of university-level matches, annotated for multi-object tracking, game state reconstruction, and ball action spotting, including 12 action classes.
SoccerTrack v2 is a new public dataset for advancing multi-object tracking (MOT), game state reconstruction (GSR), and ball action spotting (BAS) in soccer analytics. Unlike prior datasets that use broadcast views or limited scenarios, SoccerTrack v2 provides 10 full-length, panoramic 4K recordings of university-level matches, captured with BePro cameras for complete player visibility. Each video is annotated with GSR labels (2D pitch coordinates, jersey-based player IDs, roles, teams) and BAS labels for 12 action classes (e.g., Pass, Drive, Shot). This technical report outlines the datasets structure, collection pipeline, and annotation process. SoccerTrack v2 is designed to advance research in computer vision and soccer analytics, enabling new benchmarks and practical applications in tactical analysis and automated tools.