A Fuzzy Logic Based Approach for Crowd Simulation
In this article, we present a new approach which incorporates fuzzy logic with data-driven crowd simulation method. Behavior rules are derived from the state-action samples obtained from crowd videos by MLFE algorithm. The derived rules complement the disadvantages of rule-based approach in the situation where the crowd behavior can’t be reduced to rules, i.e., calibrate the behaviors produced by rule-based approach. During a simulation, the new derived rules can be combined with pre-defined ones. Then, the compositive rules are treated in the overview of fuzzy logic to simulate various crowd behaviors. It is noticeable that the derived rules can be used independently for data-driven crowd simulation or be incorporated with predefined rules. The advantages of our approach are obvious: interoperability, universality and behavior’s diversity.
Keywordscrowd simulation fuzzy logic MLFE rule extraction
Unable to display preview. Download preview PDF.
- 1.Lee, K.H., Choi, M.G., Hong, Q., Lee, J.: Group Behavior from Video: A Data-Driven Approach to Crowd Simulation. In: Proc. ACM SIGGRAPH/ Eurographics Symposium on Computer Animation, San Diego, Eurographics Association Aire-la-Ville, Switzerland, pp. 109–118 (2007)Google Scholar
- 5.Ross, T.J.: Fuzzy logic with engineering application, 3rd edn. John Wiley & Sons, Ltd. (2010)Google Scholar
- 6.Ghasem-Aghaee, N., Ören, T.I.: Towards Fuzzy Agents with Dynamic Personality for Human Behavior Simulation. In: Proceedings of the 2003 Summer Computer Simulation Conference, Montreal, PQ, Canada, pp. 3–10 (2003)Google Scholar
- 7.Thalmann, D., Raupp Musse, S.: Crowd Simulation. Springer, London (2007)Google Scholar
- 8.Pelechano, N., Allbeck, J., Badler, N.I.: Virtual Crowds: Methods, Simulation, and Control. Morgan&Claypool Publishers (2008)Google Scholar