SoccerTrack v2: A Full-Pitch Multi-View Soccer Dataset for Game State Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912517158076416 |
|---|---|
| author | Scott, Atom Uchida, Ikuma Kuroda, Kento Kim, Yufi Fujii, Keisuke |
| author_facet | Scott, Atom Uchida, Ikuma Kuroda, Kento Kim, Yufi Fujii, Keisuke |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01802 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SoccerTrack v2: A Full-Pitch Multi-View Soccer Dataset for Game State Reconstruction Scott, Atom Uchida, Ikuma Kuroda, Kento Kim, Yufi Fujii, Keisuke Computer Vision and Pattern Recognition 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. |
| title | SoccerTrack v2: A Full-Pitch Multi-View Soccer Dataset for Game State Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01802 |