Grey Level Dependent Matrix Based Crowd Density Estimation in Fourier Spectrum
Xiaohua Li · Microcomputer Information · 2008
Crowd density estimation is very important to designs of huge public works and crowd safety.In this paper,a extracting technique of crowd density feature based 2D_fast Fourier transform and grey level dependent matrix is proposed.A novel method for texture feature extraction is now proposed based on that difference of Frequency spectrum image belongs to different crowd density image.Regarding frequency spectrum image as the texture image,the texture characteristics which can represent those difference are extracted using texture analysis's method.And then crowd density level is classified by adaboost.The experimental result indicate that when the method proposed in this article is not inferior to other algorithm in rate of accuracy, speed of computing enhance distinctly.