UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning Extremely High Density Crowds as Active Matters

He, F; Yue, J; Zhu, J; Seyfried, A; Casas, D; Pettré, J; Wang, H; (2025) Learning Extremely High Density Crowds as Active Matters. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. (pp. pp. 540-550). IEEE: Nashville, TN, USA. Green open access

[thumbnail of 2409.18401v1.pdf]
Preview
Text
2409.18401v1.pdf - Accepted Version

Download (21MB) | Preview

Abstract

Video-based high-density crowd analysis and prediction has been a long-standing topic in computer vision. It is notoriously difficult due to, but not limited to, the lack of high-quality data and complex crowd dynamics. Consequently, it has been relatively under-studied. In this paper, we propose a new approach that aims to learn from in-the-wild videos, often with low quality where it is difficult to track individuals or count heads. The key novelty is a new physics prior to model crowd dynamics. We model high-density crowds as active matter, a continuum with active particles subject to stochastic forces, named 'crowd material'. Our physics model is combined with neural networks, resulting in a neural stochastic differential equation system that can mimic complex crowd dynamics. Due to the lack of similar research, we adapt a range of existing methods which are close to ours for comparison. Through exhaustive evaluations, we show our model outperforms existing methods in analyzing and forecasting extremely high-density crowds. Furthermore, since our model is a continuous-time physics model, it can be used for simulation and analysis, providing strong interpretability. This is categorically different from most deep learning methods, which are discrete-time models and black-boxes.

Type: Proceedings paper
Title: Learning Extremely High Density Crowds as Active Matters
Event: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Dates: 10 Jun 2025 - 17 Jun 2025
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR52734.2025.00059
Publisher version: https://doi.org/10.1109/cvpr52734.2025.00059
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10215207
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item