Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909404078538752 |
|---|---|
| author | Stanczyk, Tomasz Bremond, Francois |
| author_facet | Stanczyk, Tomasz Bremond, Francois |
| contents | Multi-object tracking (MOT) involves identifying and consistently tracking objects across video sequences. Traditional tracking-by-detection methods, while effective, often require extensive tuning and lack generalizability. On the other hand, segmentation mask-based methods are more generic but struggle with tracking management, making them unsuitable for MOT. We propose a novel approach, McByte, which incorporates a temporally propagated segmentation mask as a strong association cue within a tracking-by-detection framework. By combining bounding box and propagated mask information, McByte enhances robustness and generalizability without per-sequence tuning. Evaluated on four benchmark datasets - DanceTrack, MOT17, SoccerNet-tracking 2022, and KITTI-tracking - McByte demonstrates performance gain in all cases examined. At the same time, it outperforms existing mask-based methods. Implementation code will be provided upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_14220 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking Stanczyk, Tomasz Bremond, Francois Computer Vision and Pattern Recognition Multi-object tracking (MOT) involves identifying and consistently tracking objects across video sequences. Traditional tracking-by-detection methods, while effective, often require extensive tuning and lack generalizability. On the other hand, segmentation mask-based methods are more generic but struggle with tracking management, making them unsuitable for MOT. We propose a novel approach, McByte, which incorporates a temporally propagated segmentation mask as a strong association cue within a tracking-by-detection framework. By combining bounding box and propagated mask information, McByte enhances robustness and generalizability without per-sequence tuning. Evaluated on four benchmark datasets - DanceTrack, MOT17, SoccerNet-tracking 2022, and KITTI-tracking - McByte demonstrates performance gain in all cases examined. At the same time, it outperforms existing mask-based methods. Implementation code will be provided upon acceptance. |
| title | Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.14220 |