Crowd density estimation method based on floor area

Abstract

Crowd density estimation is a hot issue in the analysis of crowd abnormal behavior. At present, the crowd density is calculated by the ratio of population and area. However, these methods ignore the influence of monitoring perspective and local crowd distribution in the selection and processing of area. In this paper, we propose a crowd density estimation method based on the floor area, which can accurately estimate the density of low and medium density crowd. Based on crowd density estimation, we propose a new division method of crowd density rank, which can effectively judge the crowd density rank at each moment. The proposed method is executed by the data sets of Mall, Smarty City and USCD. The experimental results show that proposed method can effectively estimate the crowd density value in the low and medium density crowd.