MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917897371123712 |
|---|---|
| author | Huang, Hsiang-Wei Yang, Cheng-Yen Chai, Wenhao Jiang, Zhongyu Hwang, Jenq-Neng |
| author_facet | Huang, Hsiang-Wei Yang, Cheng-Yen Chai, Wenhao Jiang, Zhongyu Hwang, Jenq-Neng |
| contents | In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman filter with a learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman filter-based tracker. In this paper, our proposed method MambaMOT and MambaMOT+, demonstrate advanced performance on challenging MOT datasets such as DanceTrack and SportsMOT, showcasing their ability to handle intricate, non-linear motion patterns and frequent occlusions more effectively than traditional methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10826 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking Huang, Hsiang-Wei Yang, Cheng-Yen Chai, Wenhao Jiang, Zhongyu Hwang, Jenq-Neng Computer Vision and Pattern Recognition In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman filter with a learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman filter-based tracker. In this paper, our proposed method MambaMOT and MambaMOT+, demonstrate advanced performance on challenging MOT datasets such as DanceTrack and SportsMOT, showcasing their ability to handle intricate, non-linear motion patterns and frequent occlusions more effectively than traditional methods. |
| title | MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.10826 |