Robust upper body detection in unconstrained posture

This paper presents an efficient approach to detecting upper body in unconstrained posture based on Shape Context and Histograms of Orient Gradients. The method contains two steps. Shape context matching is used to get the candidates of upper bodies in the images at first, and then validation of each candidate is performed by using the Histograms of Orient Gradients. The method has two advantages, comparing with existing body detection methods. One is that it can detect upper bodies in all kinds of postures other than upright standing posture, and the other is that it significantly speeds up the computation.