EUVIMEDEUVIMED entdecken
Crossref

Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos

Jianbo Ma, Hui Luo, Qi Chen, Yuankai Qi, Yumei Sun, Amin Beheshti, Jianlin Zhang, Ming-Hsuan Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (10) · 7773-7781

DOI: 10.1609/aaai.v40i10.37720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jianbo Ma und 7 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.

Zitieren

APA

Ma, J., Luo, H., Chen, Q., Qi, Y., Sun, Y., Beheshti, A., Zhang, J., & Yang, M. (2026). Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos. Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 7773-7781. https://doi.org/10.1609/aaai.v40i10.37720

Vancouver

Ma J, Luo H, Chen Q, Qi Y, Sun Y, Beheshti A, et al. Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(10):7773-7781. doi:10.1609/aaai.v40i10.37720

BibTeX
@article{Ma2026,
  author = {Ma, Jianbo and Luo, Hui and Chen, Qi and Qi, Yuankai and Sun, Yumei and Beheshti, Amin and Zhang, Jianlin and Yang, Ming-Hsuan},
  title = {Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {10},
  pages = {7773--7781},
  doi = {10.1609/aaai.v40i10.37720}
}
Kostenlos starten →