ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909299213598720 |
|---|---|
| author | Jiang, Lifan Wang, Zhihui Yin, Siqi Ma, Guangxiao Zhang, Peng Wu, Boxi |
| author_facet | Jiang, Lifan Wang, Zhihui Yin, Siqi Ma, Guangxiao Zhang, Peng Wu, Boxi |
| contents | Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects in real-time across various scenarios. However, these methods still face challenges such as poor noise resistance and frequent ID switches. In this research, we propose a novel ConsistencyTrack, joint detection and tracking(JDT) framework that formulates detection and association as a denoising diffusion process on perturbed bounding boxes. This progressive denoising strategy significantly improves the model's noise resistance. During the training phase, paired object boxes within two adjacent frames are diffused from ground-truth boxes to a random distribution, and then the model learns to detect and track by reversing this process. In inference, the model refines randomly generated boxes into detection and tracking results through minimal denoising steps. ConsistencyTrack also introduces an innovative target association strategy to address target occlusion. Experiments on the MOT17 and DanceTrack datasets demonstrate that ConsistencyTrack outperforms other compared methods, especially better than DiffusionTrack in inference speed and other performance metrics. Our code is available at https://github.com/Tankowa/ConsistencyTrack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15548 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model Jiang, Lifan Wang, Zhihui Yin, Siqi Ma, Guangxiao Zhang, Peng Wu, Boxi Computer Vision and Pattern Recognition Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects in real-time across various scenarios. However, these methods still face challenges such as poor noise resistance and frequent ID switches. In this research, we propose a novel ConsistencyTrack, joint detection and tracking(JDT) framework that formulates detection and association as a denoising diffusion process on perturbed bounding boxes. This progressive denoising strategy significantly improves the model's noise resistance. During the training phase, paired object boxes within two adjacent frames are diffused from ground-truth boxes to a random distribution, and then the model learns to detect and track by reversing this process. In inference, the model refines randomly generated boxes into detection and tracking results through minimal denoising steps. ConsistencyTrack also introduces an innovative target association strategy to address target occlusion. Experiments on the MOT17 and DanceTrack datasets demonstrate that ConsistencyTrack outperforms other compared methods, especially better than DiffusionTrack in inference speed and other performance metrics. Our code is available at https://github.com/Tankowa/ConsistencyTrack. |
| title | ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.15548 |