Crowd Density Field Estimation Based on Crowd Dynamics Theory and Social Force Model

作     者：WEI Xinlei DU Junping LIANG Meiyu XUE Zhe WEI Xinlei;DU Junping;LIANG Meiyu;XUE Zhe

作者机构：Beijing Key Lab of Intelligent Telecommunication Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications 

出 版 物：《Chinese Journal of Electronics》 (电子学报(英文))

年 卷 期：2019年第28卷第3期

页      面：521-528页

核心收录：

学科分类：030603[法学-治安学] 03[法学] 08[工学] 080203[工学-机械设计及理论] 0838[工学-公安技术] 0802[工学-机械工程] 0306[法学-公安学] 

基　　金：supported by the National Natural Science Foundation of China(No.61532006 No.61772083 No.61877006 No.61802028) 

主　　题：Social force model Crowd dynamics Crowd density field Computer vision 

摘      要：The local crowd density and the crowd distribution estimation tasks are useful but *** are two main problems which limit the performance of existing algorithms. The first one is that there are not enough labeled training samples to build the highperformance estimation model. Another one is that existing methods lack the supports of physical theories of the crowd. To remedy them, a novel crowd density field model is proposed, which is deduced by jointing crowd dynamics theory and social force model. A crowd counting method based on the proposed crowd density field model is introduced to measure the proposed crowd density field model. Extensive experiments confirm the effectiveness of the proposed plan.