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.

We investigate a new task in human motion prediction, which is predicting motions under unexpected physical perturbation potentially involving multiple people. Compared with existing research, this task involves predicting less controlled, unpremeditated and pure reactive motions in response to external impact and how such motions can propagate through people. It brings new challenges such as data scarcity and predicting complex interactions. To this end, we propose a new method capitalizing differentiable physics and deep neural networks, leading to an explicit Latent Differentiable Physics (LDP) model. Through experiments, we demonstrate that LDP has high data efficiency, outstanding prediction accuracy, strong generalizability and good explainability. Since there is no similar research, a comprehensive comparison with 11 adapted baselines from several relevant domains is conducted, showing LDP outperforming existing research both quantitatively and qualitatively, improving prediction accuracy by as much as 70%, and demonstrating significantly stronger generalization.

ABSTRACT To improve safety at mass events, an evacuation assistant that supports security services in case of emergencies is developed. One central aspect is forecasting the emergency egress of large crowds in complex buildings. This requires realistic models of pedestrian dynamics that can be simulated faster than real‐time by using methods applied in high performance computing. We give an overview of the project and present the actual results. We also describe the modeling approaches used thereby focusing on the runtime optimization and parallelization concepts. Copyright © 2012 John Wiley & Sons, Ltd.

In recent years, several approaches for modelling pedestrian dynamics have been proposed. However, so far not much attention has been paid to their quantitative validation. Instead the focus has been on the reproduction of empirically observed collective phenomena like the dynamical formation of lanes. Although this gives an indication of the realism of the model, for practical applications as in safety analysis, reliable quantitative predictions are required. We discuss the experimental situation focusing on the fundamental diagram that is essential for calibration. Furthermore, we present a cellular automaton, the floor field model, which forms the basis for various multi-agent simulations. Apart from the properties of its fundamental diagram, we discuss the role of conflicts and friction effects and their influence on evacuation times.

We introduce a new class of parallel algorithms for the exact computation of systems with pairwise mutual interactions of n elements, so called n/sup 2/-problems. Hitherto, practical conventional parallelization strategies could achieve a complexity of O(np) with respect to the inter-processor communication, p being the number of processors. Our new approach can reduce the inter-processor communication complexity to a number O(np). In the framework of Additive Number Theory, the determination of the optimal communication pattern can be formulated as h-range minimization problem that can be solved numerically. Based on a complexity model, the scaling behavior of the new algorithm is numerically tested on the connection machine CM5. As a real life example, we have implemented a fast code for globular cluster n-body simulations, a generic n/sup 2/-problem, on the CRAY T3D, with striking success. Our parallel method promises to be useful in various scientific and engineering fields like polymer chain computations, protein folding, signal processing, and, in particular, for parallel level-3 BLAS.