DiffusionTrack: Diffusion Model for Multi-Object Tracking
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 3991-3999
DOI: 10.1609/aaai.v38i5.28192 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Run Luo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 75-mal zitiert (Crossref).
Abstract (Originalsprache)
Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection (TBD) methods and one-stage joint detection and tracking (JDT) methods. Despite the success of these approaches, they also suffer from common problems, such as harmful global or local inconsistency, poor trade-off between robustness and model complexity, and lack of flexibility in different scenes within the same video. In this paper we propose a simple but robust framework that formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes. This novel progressive denoising diffusion strategy substantially augments the tracker's effectiveness, enabling it to discriminate between various objects. During the training stage, paired object boxes diffuse from paired ground-truth boxes to random distribution, and the model learns detection and tracking simultaneously by reversing this noising process. In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process. Extensive experiments on three widely used MOT benchmarks, including MOT17, MOT20, and DanceTrack, demonstrate that our approach achieves competitive performance compared to the current state-of-the-art methods. Code is available at https://github.com/RainBowLuoCS/DiffusionTrack.
Zitieren
APA
Luo, R., Song, Z., Ma, L., Wei, J., Yang, W., & Yang, M. (2024). DiffusionTrack: Diffusion Model for Multi-Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 3991-3999. https://doi.org/10.1609/aaai.v38i5.28192
Vancouver
Luo R, Song Z, Ma L, Wei J, Yang W, Yang M. DiffusionTrack: Diffusion Model for Multi-Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):3991-3999. doi:10.1609/aaai.v38i5.28192
BibTeX
@article{Luo2024,
author = {Luo, Run and Song, Zikai and Ma, Lintao and Wei, Jinlin and Yang, Wei and Yang, Min},
title = {DiffusionTrack: Diffusion Model for Multi-Object Tracking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {5},
pages = {3991--3999},
doi = {10.1609/aaai.v38i5.28192}
}
EUVIMED