 |
    |
Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation
Yuandong Tian1, C. Lawrence Zitnick2, and Srinivasa G. Narasimhan1
1Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213, USA
yuandong@cs.cmu.edu
srinivas@cs.cmu.edu
2Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA
larryz@microsoft.com
Abstract. Human pose estimation requires a versatile yet well-constrained spatial model for grouping locally ambiguous parts together to produce a globally consistent hypothesis. Previous works either use local deformable models deviating from a certain template, or use a global mixture representation in the pose space. In this paper, we propose a new hierarchical spatial model that can capture an exponential number of poses with a compact mixture representation on each part. Using latent nodes, it can represent high-order spatial relationship among parts with exact inference. Different from recent hierarchical models that associate each latent node to a mixture of appearance templates (like HoG), we use the hierarchical structure as a pure spatial prior avoiding the large and often confounding appearance space. We verify the effectiveness of this model in three ways. First, samples representing human-like poses can be drawn from our model, showing its ability to capture high-order dependencies of parts. Second, our model achieves accurate reconstruction of unseen poses compared to a nearest neighbor pose representation. Finally, our model achieves state-of-art performance on three challenging datasets, and substantially outperforms recent hierarchical models.
LNCS 7576, p. 256 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012