GTATrack: Winner Solution to SoccerTrack 2025 with Deep-EIoU and Global Tracklet Association
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912866130460672 |
|---|---|
| author | Jian, Rong-Lin Luo, Ming-Chi Huang, Chen-Wei Lee, Chia-Ming Lin, Yu-Fan Hsu, Chih-Chung |
| author_facet | Jian, Rong-Lin Luo, Ming-Chi Huang, Chen-Wei Lee, Chia-Ming Lin, Yu-Fan Hsu, Chih-Chung |
| contents | Multi-object tracking (MOT) in sports is highly challenging due to irregular player motion, uniform appearances, and frequent occlusions. These difficulties are further exacerbated by the geometric distortion and extreme scale variation introduced by static fisheye cameras. In this work, we present GTATrack, a hierarchical tracking framework that win first place in the SoccerTrack Challenge 2025. GTATrack integrates two core components: Deep Expansion IoU (Deep-EIoU) for motion-agnostic online association and Global Tracklet Association (GTA) for trajectory-level refinement. This two-stage design enables both robust short-term matching and long-term identity consistency. Additionally, a pseudo-labeling strategy is used to boost detector recall on small and distorted targets. The synergy between local association and global reasoning effectively addresses identity switches, occlusions, and tracking fragmentation. Our method achieved a winning HOTA score of 0.60 and significantly reduced false positives to 982, demonstrating state-of-the-art accuracy in fisheye-based soccer tracking. Our code is available at https://github.com/ron941/GTATrack-STC2025. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00484 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GTATrack: Winner Solution to SoccerTrack 2025 with Deep-EIoU and Global Tracklet Association Jian, Rong-Lin Luo, Ming-Chi Huang, Chen-Wei Lee, Chia-Ming Lin, Yu-Fan Hsu, Chih-Chung Computer Vision and Pattern Recognition Multimedia Multi-object tracking (MOT) in sports is highly challenging due to irregular player motion, uniform appearances, and frequent occlusions. These difficulties are further exacerbated by the geometric distortion and extreme scale variation introduced by static fisheye cameras. In this work, we present GTATrack, a hierarchical tracking framework that win first place in the SoccerTrack Challenge 2025. GTATrack integrates two core components: Deep Expansion IoU (Deep-EIoU) for motion-agnostic online association and Global Tracklet Association (GTA) for trajectory-level refinement. This two-stage design enables both robust short-term matching and long-term identity consistency. Additionally, a pseudo-labeling strategy is used to boost detector recall on small and distorted targets. The synergy between local association and global reasoning effectively addresses identity switches, occlusions, and tracking fragmentation. Our method achieved a winning HOTA score of 0.60 and significantly reduced false positives to 982, demonstrating state-of-the-art accuracy in fisheye-based soccer tracking. Our code is available at https://github.com/ron941/GTATrack-STC2025. |
| title | GTATrack: Winner Solution to SoccerTrack 2025 with Deep-EIoU and Global Tracklet Association |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2602.00484 |