Abstract.
We present a novel algorithm for performing integrated seg- mentation and 3D pose estimation of a human body from multiple views. Unlike other related state of the art techniques which focus on either segmentation or pose estimation individually, our approach tackles these two tasks together. Normally, when optimizing for pose, it is traditional to use some fixed set of features, e.g. edges or chamfer maps. In con- trast, our novel approach consists of optimizing a cost function based on a Markov Random Field (MRF). This has the advantage that we can use all the information in the image: edges, background and foreground appearances, as well as the prior information on the shape and pose of the sub ject and combine them in a Bayesian framework. Previously, opti- mizing such a cost function would have been computationally infeasible. However, our recent research in dynamic graph cuts allows this to be done much more e?ciently than before. We demonstrate the e?cacy of our approach on challenging motion sequences. Note that although we target the human pose inference problem in the paper, our method is completely generic and can be used to segment and infer the pose of any speci?ed rigid, deformable or articulated ob ject.