EUVIMEDEUVIMED entdecken
Crossref

Crowded Video Individual Counting Informed by Social Grouping and Spatial–Temporal Displacement Priors

Hao Lu, Xuhui Zhu, Wenjing Zhang, Yanan Li, Xiang Bai

IEEE Transactions on Image Processing · 2026 · 35 · 11508-11523

DOI: 10.1109/tip.2026.3737046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Hao Lu und 4 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Research Project of Hubei Provincial Department of Education, Wuhan Natural Science Foundation Exploration Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Video Individual Counting (VIC) is a recently introduced task aiming to estimate foot traffic from a video. It extends Video Crowd Counting (VCC) beyond the per-frame pedestrian count. In contrast to VCC that learns to count pedestrians across frames, VIC must identify co-existent pedestrians between frames, which turns out to be a correspondence problem. Existing VIC approaches, however, can underperform in congested scenes such as metro commuting. To address this, we build WuhanMetroCrowd, one of the first VIC datasets that characterize crowded, dynamic pedestrian flows. It features sparse-to-dense density levels, short-to-long video clips, slow-to-fast flow variations, front-to-back appearance changes, and light-to-heavy occlusions. To better adapt VIC approaches to crowds, we rethink the nature of VIC and recognize two informative priors: I) the social grouping prior that indicates pedestrians tend to gather in groups and II) the spatial-temporal displacement prior that informs an individual cannot teleport physically. The former inspires us to relax the standard one-to-one (O2O) matching used by VIC to one-to-many (O2M) matching, implemented by an implicit context generator and an O2M matcher; the latter facilitates the design of a displacement prior injector, which strengthens not only O2M matching but also feature extraction and model training. These designs jointly form a novel and strong VIC baseline OMAN++. Extensive experiments show that OMAN++ not only outperforms state-of-the-art VIC baselines on the standard SenseCrowd, CroHD, and MovingDroneCrowd benchmarks, but also indicates a clear advantage in crowded scenes, with a 41.8% error reduction on our WuhanMetroCrowd dataset. Code, data, and pretrained models are available at https://github.com/tiny-smart/OMAN.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Research Project of Hubei Provincial Department of Education
  • Wuhan Natural Science Foundation Exploration Program
  • Scientific Research Foundation of Wuhan Institute of Technology

Zitieren

APA

Lu, H., Zhu, X., Zhang, W., Li, Y., & Bai, X. (2026). Crowded Video Individual Counting Informed by Social Grouping and Spatial–Temporal Displacement Priors. IEEE Transactions on Image Processing, 35, 11508-11523. https://doi.org/10.1109/tip.2026.3737046

Vancouver

Lu H, Zhu X, Zhang W, Li Y, Bai X. Crowded Video Individual Counting Informed by Social Grouping and Spatial–Temporal Displacement Priors. IEEE Transactions on Image Processing. 2026;35:11508-11523. doi:10.1109/tip.2026.3737046

BibTeX
@article{Lu2026,
  author = {Lu, Hao and Zhu, Xuhui and Zhang, Wenjing and Li, Yanan and Bai, Xiang},
  title = {Crowded Video Individual Counting Informed by Social Grouping and Spatial–Temporal Displacement Priors},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {11508--11523},
  doi = {10.1109/tip.2026.3737046}
}
Kostenlos starten →