Revisiting pose estimation with foreshortening compensation and color information

This paper addresses the problem of upper body pose estimation. The task is to detect and estimate 2D human configuration in static images for six parts: head, torso, and left-right upper and lower arms. The common approach to solve this has been the Pictorial Structure method (Felzenszwalb and Huttenlocher, 2005). We present this as a graphical model inference problem and use the loopy belief propagation algorithm for inference. When a human appears in fronto-parallel plane, fixed size part detectors are sufficient and give reliable detection. But when parts like lower and upper arms move out of the plane, we observe foreshortening and the part detectors become erroneous. We propose an approach that compensates foreshortening in the upper and lower arms, and effectively prunes the search state space of each part. Additionally, we introduce two extra pairwise constraints to exploit the color similarity information between parts during inference to get better localization of the upper and lower arms. Finally, we present experiments and results on two challenging datasets (Buffy and ETHZ Pascal), showing improvements on the lower arms accuracy and comparable results for other parts.