CLUST: Simulating Realistic Crowd Behaviour by Mining Pattern from Crowd Videos
Authors:
- 19 July 2017
- journal article
- research article
- Published by Wiley in Computer Graphics Forum
- Vol. 37 (1) , 184-201
Abstract
In this paper, we present a data‐driven approach to simulate realistic locomotion of virtual pedestrians. We focus on simulating low‐level pedestrians' motion, where a pedestrian's motion is mainly affected by other pedestrians and static obstacles nearby, and the preferred velocities of agents (direction and speed) are obtained from higher level path planning models. Before the simulation, collision avoidance processes (i.e. examples) are extracted from videos to describe how pedestrians avoid collisions, which are then clustered using hierarchical clustering algorithm with a novel distance function to find similar patterns of pedestrians' collision avoidance behaviours. During the simulation, at each time step, the perceived state of each agent is classified into one cluster using a neural network trained before the simulation. A sequence of velocity vectors, representing the agent's future motion, is selected among the examples corresponding to the chosen cluster. The proposed CLUST model is trained and applied to different real‐world datasets to evaluate its generality and effectiveness both qualitatively and quantitatively. The simulation results demonstrate that the proposed model can generate realistic crowd behaviours with comparable computational cost.Keywords
This publication has 59 references indexed in Scilit:
- Morphable crowdsACM Transactions on Graphics, 2010
- The Walking Behaviour of Pedestrian Social Groups and Its Impact on Crowd DynamicsPLOS ONE, 2010
- State of the Art in Example‐Based Motion Synthesis for Virtual Characters in Interactive ApplicationsComputer Graphics Forum, 2010
- Experimental study of the behavioural mechanisms underlying self-organization in human crowdsProceedings Of The Royal Society B-Biological Sciences, 2009
- Human Behavior Models for Agents in Simulators and Games: Part I: Enabling Science with PMFservPRESENCE: Virtual and Augmented Reality, 2006
- Experimental Research of Pedestrian Walking BehaviorTransportation Research Record: Journal of the Transportation Research Board, 2003
- Emergent Fundamental Pedestrian Flows from Cellular Automata MicrosimulationTransportation Research Record: Journal of the Transportation Research Board, 1998
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- Efficient algorithms for agglomerative hierarchical clustering methodsJournal of Classification, 1984
- Erving Goffman, Relations in public: microstudies of the public order. New York: Basic Books, 1971. Pp. xvii + 396.Language in Society, 1972