Marker-less motion capture of skinned models in a four camera set-up using optical flow and silhouettes

Abstract

We explore a new approach to marker-less motion tracking of a priori known skinned meshes using both optical flow and silhouette information. We present a formulation which considers in a unified way both these two kinds of information and accounts for the non-rigid deformations of the object skin modeling them using the Skeletal Subspace Deformation (SSD). We then demonstrate the effectiveness of our technique showing its performance in a four camera set-up tracking a subject modeled by a skeleton with 46 degrees of freedom.