Metraipolis › archive › dc_ae5ae1b4e6a3

The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking — arXiv:2610.19369

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19369
License (as archived)
CC0-1.0
Archived
2026-10-15T14:23:21.163Z
SHA-256 of the archived text
36b49423b362f70ee03e35463e5992603b96c2478cd0fab8b52f063d41aa1fbb
Stable URL of this page
https://metraipolis.com/documento/dc_ae5ae1b4e6a3

How to cite

The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking — arXiv:2610.19369 — arXiv (en), https://arxiv.org/abs/2610.19369 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae5ae1b4e6a3 (Metraipolis archive dc_ae5ae1b4e6a3, sha256 36b49423b362f70ee03e35463e5992603b96c2478cd0fab8b52f063d41aa1fbb)
BibTeX
@misc{dcae5ae1b4e6a3,
  title = {The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking — arXiv:2610.19369},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19369},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae5ae1b4e6a3; sha256 36b49423b362f70ee03e35463e5992603b96c2478cd0fab8b52f063d41aa1fbb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19369. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pedestrian tracking in video is important for applications such as surveillance and scene analysis, but it becomes more challenging in crowded scenarios with frequent occlusions and rapid motion. This paper analyzes how detector architecture, model scale, scene density, and inference regime affect the tracking of multiple pedestrians. We compare the YOLO11, RT-DETR, and YOLO26 detector families with the ByteTrack and BoT-SORT trackers on sequences from the MOT17, MOT20, and SOMPT22 benchmarks. For YOLO26, we also compare traditional overlap filtering via Non-Maximum Suppression (NMS) with end-to-end inference. The RT-DETR family achieved the highest mean scores on the HOTA tracking quality metric across all three benchmarks with both trackers, with a more pronounced advantage on MOT20, albeit at a higher computational cost. On MOT17 and SOMPT22, YOLO26 variants, especially YOLO26-L with NMS, offered favorable combinations of quality and speed compared with RT-DETR. In the YOLO26 inference comparison, the end-to-end mode did not yield consistent tracking gains over the NMS-based regime. Taken together, these results provide a practical guide for selecting detectors and trackers for this task based on application priorities.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.19369 — 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 2026-10-15T13:53:35.853Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).