When Physics Meets AI: Modelling High-Density Crowds In Videos with Deep Learning

Abstract:
Deep neural networks (DNNs) have rapidly transformed many fields, often replacing traditional explicit models despite their "black box" nature. However, explicit models encapsulate valuable human knowledge, and rather than discarding them, a powerful research trend has emerged: combining them with DNNs. Initially applied to fluid dynamics in 2016, this approach—now known as AI for Science—has since expanded across disciplines.
In this talk, I will demonstrate how physics-informed deep learning extends far beyond solving physics problems. I will showcase how we leverage this approach to analyse pedestrian dynamics from video data, tackling some of the most challenging real-world scenarios, including ultra-dense crowds where the risk of crushes is high. By fusing physics with AI, we uncover deeper insights and push the boundaries of what’s possible in modelling complex human behaviours.

Speaker:
He Wang is an Associate Professor in the Department of Computer Science at University College London, a core member of the UCL Centre for Artificial Intelligence, and a Visiting Professor at the University of Leeds. His research focuses on computer graphics, computer vision, scientific machine learning, and deep learning. Previously, he was an Associate Professor at the University of Leeds and a Senior Research Associate at Disney Research Los Angeles. He has led or co-led research projects of several million pounds funded by the EU and UKRI. He is a former Turing Fellow and also serves as an Associate Editor for Computer Graphics Forum, an Academic Advisor at the Commonwealth Scholarship Council, and has held key roles in major international conferences.