Deep Learning Improved Social Force Model to Simulate Crowd in Varying Scenes

Dapeng Yan*, Chongzhi Bai, Lian He, Gangyi Ding

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Traditional social force models are capable of simulating various types of crowds, but due to their reliance on a single formula and simplified parameter control, they often lack realism when applied to crowd scenes. The integration of deep learning with social force models has already achieved success in pedestrian simulation tasks in specific scenarios, yet research in more generalized scenes is still lacking. Therefore, we have used deep learning in conjunction with social force models to construct crowd simulations in various scenarios. This model is based on the dynamics of crowd trajectories and refines key parameters of the social force model using deep learning methods. Experimental results prove that this model can effectively adapt to diverse environments different from the scenes on which the training data is based.

Original languageEnglish
Title of host publication2024 7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages307-312
Number of pages6
ISBN (Electronic)9798350361445
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024 - Hybrid, Shanghai, China
Duration: 1 Mar 20243 Mar 2024

Publication series

Name2024 7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024

Conference

Conference7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024
Country/TerritoryChina
CityHybrid, Shanghai
Period1/03/243/03/24

Keywords

  • Crowd Simulation
  • Deep Learning
  • Multi-Agent
  • Social Force Model

Cite this