ABSTRACT
This paper presents a novel data-driven crowd simulation method that can mimic the observed traffic of pedestrians in a given environment. Given a set of observed trajectories, we use a recent form of neural networks, Generative Adversarial Networks (GANs), to learn the properties of this set and generate new trajectories with similar properties. We define a way for simulated pedestrians (agents) to follow such a trajectory while handling local collision avoidance. As such, the system can generate a crowd that behaves similarly to observations, while still enabling real-time interactions between agents. Via experiments with real-world data, we show that our simulated trajectories preserve the statistical properties of their input. Our method simulates crowds in real time that resemble existing crowds, while also allowing insertion of extra agents, combination with other simulation methods, and user interaction.
- Amirian, J., Hayet, J.-B., and Pettré, J. Social ways: Learning multi-modal distributions of pedestrian trajectories with GANs. In CVPR Workshops (2019).Google ScholarCross Ref
- van den Berg, J., Guy, S., Lin, M., and Manocha, D. Reciprocal n-body collision avoidance. In Proc. Int. Symp. Robotics Research (2011), pp. 3--19.Google ScholarCross Ref
- Di, X., and Patel, V. Face synthesis from visual attributes via sketch using conditional VAEs and GANs. CoRR abs/1801.00077 (2018).Google Scholar
- Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. Generative adversarial nets. In Proc. Int. Conf. Neural Information Processing Systems (2014), vol. 2, pp. 2672--2680. Google ScholarDigital Library
- Helbing, D., and Molnár, P. Social force model for pedestrian dynamics. Physical Review E 51, 5 (1995), 4282--4286.Google ScholarCross Ref
- Jaklin, N., Cook IV, A., and Geraerts, R. Real-time path planning in heterogeneous environments. Computer Animation and Virtual Worlds 24, 3 (2013), 285--295.Google ScholarCross Ref
- Lee, K., Choi, M., Hong, Q., and Lee, J. Group behavior from video: A data-driven approach to crowd simulation. In Proc. ACM SIGGRAPH/Eurographics Symp. Computer Animation (2007), pp. 109--118. Google ScholarDigital Library
- Lerner, A., Chrysanthou, Y., and Lischinski, D. Crowds by example. Computer Graphics Forum 26, 3 (2007), 655--664.Google ScholarCross Ref
- Metz, L., Poole, B., Pfau, D., and Sohl-Dickstein, J. Unrolled generative adversarial networks. CoRR abs/1611.02163 (2017).Google Scholar
- Pellegrini, S., Ess, A., Schindler, K., and van Gool, L. You'll never walk alone: Modeling social behavior for multi-target tracking. In Proc. IEEE Int. Conf. Computer Vision (2009), pp. 261--268.Google ScholarCross Ref
- Pellegrini, S., Gall, J., Sigal, L., and van Gool, L. Destination flow for crowd simulation. In Proc. European Conf. Computer Vision (2012), pp. 162--171. Google ScholarDigital Library
- van Toll, W., Jaklin, N., and Geraerts, R. Towards believable crowds: A generic multi-level framework for agent navigation. In ASCI.OPEN/ICT.OPEN (ASCI track) (2015).Google Scholar
- Wang, H., Ondřej, J., and O'Sullivan, C. Path patterns: Analyzing and comparing real and simulated crowds. In Proc. 20th ACM SIGGRAPH Symp. Interactive 3D Graphics and Games (2016), pp. 49--57. Google ScholarDigital Library
- Wolinski, D., Guy, S., Olivier, A.-H., Lin, M., Manocha, D., and Pettré, J. Parameter estimation and comparative evaluation of crowd simulations. Computer Graphics Forum 33, 2 (2014), 303--312. Google ScholarDigital Library
- Yersin, B., Maïm, J., Pettré, J., and Thalmann, D. Crowd patches: Populating large-scale virtual environments for real-time applications. In Proc. Symp. Interactive 3D Graphics and Games (2009), pp. 207--214. Google ScholarDigital Library
- Zhong, J., Cai, W., Luo, L., and Zhao, M. Learning behavior patterns from video for agent-based crowd modeling and simulation. Autonomous Agents and Multi-Agent Systems 30, 5 (2016), 990--1019. Google ScholarDigital Library
Index Terms
- Data-Driven Crowd Simulation with Generative Adversarial Networks
Recommendations
The hierarchical behavior model for crowd simulation
VRCAI '09: Proceedings of the 8th International Conference on Virtual Reality Continuum and its Applications in IndustryWe present a hierarchical behavior model to simulate realistic crowd behaviors. This model is composed of two parts. One is the low density behavior module, emphasizing the autonomy and diversity of the behaviors. The other is high density behavior ...
Spatial indexing in agent-based crowd simulation
SimuTools '13: Proceedings of the 6th International ICST Conference on Simulation Tools and TechniquesCrowd modeling and simulation has become a critical tool for understanding crowds and predicting their behaviours. This is accomplished by modelling the characteristics and behaviours of large groups of people, as well as their interactions. Agent-based ...
A Role-dependent Data-driven Approach for High Density Crowd Behavior Modeling
SIGSIM-PADS '16: Proceedings of the 2016 ACM SIGSIM Conference on Principles of Advanced Discrete SimulationIn this paper, we propose a role-dependent data-driven modeling approach to simulate pedestrians' motion in high density scenes. It is commonly observed that pedestrians behave quite differently when walking in dense crowd. Some people explore routes ...
Comments