Human Body Detection in Static Images Using HOG & Piecewise Linear SVM

Human detection is a challenging task in many fields because it is difficult to detect humans due to their variable appearance and posture. Detecting humans accurately is the first fundamental step for many computer vision applications such as video surveillance, smart vehicles, intersection traffic analysis and so on. This paper consists of efficient human detection in static images using Histogram of Oriented Gradients (HOG) for local feature extraction and linear piecewise support vector machine (PL-SVM) classifiers. Histogram of oriented gradient (HOG) gives an accurate description of the contour of human body. HOG features are calculated by taking orientation of histogram of edge intensity in a local region. PL-SVM is nonlinear classifier that can discriminate multiview and multiposture human bodies from the images in high dimensional feature space. Each PL-SVM model form the subspace, corresponding to the cluster of special view or posture of human. This paper consists of comparison of PL-SVM and several recent SVM methods in terms of cross validation accuracy.