Part-segment features for articulated pose estimation

We propose part-segment (PS) features for estimating an articulated pose in still images. The proposed PS feature evaluates the image likelihood of each body part (e.g. head, torso, and arms) robustly to background clutter and nuisance textures on the body and clothing. In contrast to similar segmentation features, part segmentation is improved by part-specific shape priors that are optimized by training images with fully-automatically obtained seeds. The extracted PS feature is fused complementarily with gradient features using discriminative training and adaptive weighting for robust and accurate evaluation of part similarity.