摘要：In this paper, we propose a method to estimate crowd density using improved Harris and Optics Algorithm. First of all, the images are pre-processed, corner features of the crowd are detected by the improved Harris algorithm, and then the formed density point data will be analyzed. Then, we use the optics density clustering theory to analyze the corner characters of crowd density which based on the distribution of the feature points. At last, the crowd density is estimated by the machine learning algorithm. The experiments are using PETS2009 database and the self-shooting datasets. The proposed approach has been tested on a number of image sequences, and it has good performance.The results show that our approach is superior to other methods, compared to the original Harris algorithm. Our method improves the efficiency of estimation and has a significant impact on preventing the accidents of crowd area with high density.
关键词：density clustering;Harris;Optics;crowd density
