Metraipolis › archive › dc_d79ae9b57cdf

Detector-Integrated Multi-Cue Association for Occlusion-Aware UAV Multi-Object Tracking — arXiv:2611.00105

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00105
License (as archived)
CC0-1.0
Archived
2026-11-03T11:40:33.062Z
SHA-256 of the archived text
25bf42b5017084a438b9115ed61e0b8b3e6e269ef8a0b5d8400bfb024c5d0350
Stable URL of this page
https://metraipolis.com/documento/dc_d79ae9b57cdf

How to cite

Detector-Integrated Multi-Cue Association for Occlusion-Aware UAV Multi-Object Tracking — arXiv:2611.00105 — arXiv (en), https://arxiv.org/abs/2611.00105 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d79ae9b57cdf (Metraipolis archive dc_d79ae9b57cdf, sha256 25bf42b5017084a438b9115ed61e0b8b3e6e269ef8a0b5d8400bfb024c5d0350)
BibTeX
@misc{dcd79ae9b57cdf,
  title = {Detector-Integrated Multi-Cue Association for Occlusion-Aware UAV Multi-Object Tracking — arXiv:2611.00105},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00105},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d79ae9b57cdf; sha256 25bf42b5017084a438b9115ed61e0b8b3e6e269ef8a0b5d8400bfb024c5d0350},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00105. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-object tracking (MOT) in unmanned aerial vehicle (UAV) imagery is challenging because vehicles are small, visually similar, and frequently occluded, which leads to identity switches (IDSW). Appearance-based trackers such as DeepSORT rely on a standalone re-identification (ReID) network, whose per-target inference limits runtime speed, while the appearance of small or occluded vehicles remains unreliable. This paper proposes a detector-integrated multi-cue tracking framework. Lightweight projection heads are attached to the neck of the YOLOv8n detector to extract target embeddings through ROIAlign, producing detections and embeddings in a single forward pass. A multi-cue association cost then combines motion, IoU, and appearance distances with weights determined through ablation, complemented by low-score rescue and appearance-memory protection. On the UAVDT benchmark, the proposed method achieves a MOTA of 28.33, a HOTA of 31.16, and an IDF1 of 38.18 at 82.59 FPS, the best among the compared trackers in all three metrics, and reduces IDSW by 58.4\% compared with DeepSORT.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2611.00105 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:06:37.404Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).