Crowd density estimation: An improved approach
Wei Li, Xiaojuan Wu, Koichi Matsumoto, Hua-An Zhao · 2010
Crowd density estimation is important in crowd analysis and texture analysis is an efficient method to estimate crowd density, this paper proposes an improved estimation approach based on texture analysis. First, background is removed by using a combination of optical flow and background subtract method. Then according to texture analysis, a set of new feature is extracted from foreground image. Finally, a self-organizing map neural network is used for classifying different crowds. Some experimental results show compared to former crowd estimation methods, the proposed approach can carry out the estimation more accurately, the rate of true classification is 86.3% on a data set of 600 images.