SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918465092190208 |
|---|---|
| author | Hirano, Shozaburo Ukita, Norimichi |
| author_facet | Hirano, Shozaburo Ukita, Norimichi |
| contents | Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in dense scenes. We propose SAMIDARE, a framework that enhances SAM2MOT for crowded scenes through three key components: (1) density-aware mask re-generation and (2) selective memory updates, both for adaptive mask control to preserve target feature integrity, and (3) state-aware association and new track initialization, which improves robustness under mutual occlusions and frequent frame-out events. Evaluated on the SportsMOT dataset, SAMIDARE achieves state-of-the-art performance, outperforming the baseline by 2.5 HOTA and 4.2 IDF1 points on the validation set. These results demonstrate that adaptive feature management using mask control and state-aware association provide a robust and efficient solution for dense sports tracking. Code is available at https://github.com/ZabuZabuZabu/SAMIDARE |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22162 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios Hirano, Shozaburo Ukita, Norimichi Computer Vision and Pattern Recognition Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in dense scenes. We propose SAMIDARE, a framework that enhances SAM2MOT for crowded scenes through three key components: (1) density-aware mask re-generation and (2) selective memory updates, both for adaptive mask control to preserve target feature integrity, and (3) state-aware association and new track initialization, which improves robustness under mutual occlusions and frequent frame-out events. Evaluated on the SportsMOT dataset, SAMIDARE achieves state-of-the-art performance, outperforming the baseline by 2.5 HOTA and 4.2 IDF1 points on the validation set. These results demonstrate that adaptive feature management using mask control and state-aware association provide a robust and efficient solution for dense sports tracking. Code is available at https://github.com/ZabuZabuZabu/SAMIDARE |
| title | SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.22162 |