Abstract—We present a method of estimating the number of people in high density crowds (hundreds to thousands of individuals) from still images. Unlike most existing works our method uses only still images to estimate the count. At this scale, we cannot rely on just one set of features for count estimation. We, therefore, use a fusion of multiple sources, viz. interest points (SIFT), Fourier analysis, wavelet decomposition, GLCM features and head detections, to estimate the counts. Each of these sources gives a separate estimate of the count along with confidences and other statistical measures which are then combined to obtain the final estimate. We tested our method on an existing dataset of fifty images containing over 64000 individuals. Further, we added another fifty annotated images of crowds and tested on the complete dataset of hundred images containing over 87000 individuals.

Index Terms—People counting, extremely dense crowd, texture analysis.

Department of Electrical Engineering, Indian Institute of Technology, Kanpur, India.

Cite:Ankan Bansal, K S Venkatesh, "People Counting in High Density Crowds from Still Images," International Journal of Computer and Electrical Engineering vol. 7, no. 5, pp. 316-324, 2015.