Temporal Coherent Object Flow for Multi-Object Tracking
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (7) · 6978-6986
DOI: 10.1609/aaai.v39i7.32749 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Zikai Song und 6 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref).
Abstract (Originalsprache)
Multi-object tracking is a challenging vision task that requires simultaneous reasoning about object detection and object association. Conventional solutions use frame as the basic unit and typically rely on a motion predictor that exploits the appearance features to associate detected candidates, leading to insufficient adaptability to long-term associations. In this study, we propose a section-based multi-object tracking approach that integrates a temporal coherent Object Flow Tracker (OFTrack), capable of achieving simultaneous multi-frame tracking by treating multiple consecutive frames as the basic processing unit, denoted as a “section”. Our OFTrack boosts the optical flow to the object flow by employing object perception and section-based motion estimation strategies. Object perception adopts object-aware sampling and scale-aware correlation to enable precise target discrimination. Motion estimation models the correlation of different objects in multi-frames via specialized temporal-spatial attention to achieve robust association in very long videos. Additionally, to address the oscillation of unpredictable trajectories in multi-frame estimation, we have designed temporal coherent enhancement including the trajectory masking pre-training and the smoothing constraint on trajectory curves. Comprehensive experiments on several widely used benchmarks demonstrate the superior performance of our approach.
Zitieren
APA
Song, Z., Luo, R., Ma, L., Tang, Y., Chen, Y. P., Yu, J., & Yang, W. (2025). Temporal Coherent Object Flow for Multi-Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 39(7), 6978-6986. https://doi.org/10.1609/aaai.v39i7.32749
Vancouver
Song Z, Luo R, Ma L, Tang Y, Chen YP, Yu J, et al. Temporal Coherent Object Flow for Multi-Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(7):6978-6986. doi:10.1609/aaai.v39i7.32749
BibTeX
@article{Song2025,
author = {Song, Zikai and Luo, Run and Ma, Lintao and Tang, Ying and Chen, Yi-Ping Phoebe and Yu, Junqing and Yang, Wei},
title = {Temporal Coherent Object Flow for Multi-Object Tracking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {7},
pages = {6978--6986},
doi = {10.1609/aaai.v39i7.32749}
}
EUVIMED