Crowd Estimation Using Region-Specific HOG With SVM

Abstract

Algorithms that perform crowd estimation are dependent on crowd levels. The two approaches to crowd estimation discussed are the model-based and texture-based approaches. The aim of this work is to determine the precision, recall and F-measure of the two algorithms, Histogram of Oriented Gradients (HOG) with Support Vector Machines (SVM) and Region-Specific HOG, for estimating the number of people in high and low crowd levels, respectively, in an indoor area installed with a surveillance camera, while considering the camera’s position and its field of view.