Human Pose Estimation Using Learnt Probabilistic Region Similarities and Partial Configurations

Abstract. A model of human appearance is presented for efficient pose estimation from real-world images. In common with related approaches, a high-level model defines a space of configurations which can be associated with image measurements and thus scored. A search is performed to identify good configuration(s). Such an approach is challenging because the configuration space is high dimensional, the search is global, and the appearance of humans in images is complex due to background clutter, shape uncertainty and texture. The system presented here is novel in several respects. The formulation allows differing numbers of parts to be parameterised and allows poses of differing dimensionality to be compared in a principled manner based upon learnt likelihood ratios. In contrast with current approaches, this allows a part based search in the presence of self occlusion. Furthermore, it provides a principled automatic approach to other object occlusion. View based probabilistic models of b...

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Timothy J. Roberts, Stephen J. McKenna, Ian W. Ricketts
• Keywords: Adjacent Background Appearance, Appearance Distributions, Computer Vision, ECCV 2004, Learnt Likelihood Ratios, Principled Automatic Approach, Rigid Geometric Primitives