Segmentation and probabilistic registration of articulated body models

There are different approaches to pose estimation and registration of different body parts using voxel data. We propose a general bottom-up approach in order to segment the voxels into different body parts, The voxels are first transformed into a high dimensional space which is the eigenspace of the Laplacian of the neighbourhood graph, We exploit the properties of this transformation and fit splines to the voxels belonging to different body segments in eigenspace. The boundary of the splines is determined by examination of the error in spline fitting, We then use a probabilistic approach to register the segmented body segments by utilizing their connectivity and prior knowledge of the general structure of the subjects, We present results on real data, containing both simple and complex poses. While we use human subjects in our experiment, the method is fairly general and can be applied to voxel-based registration of any articulated or non-rigid object composed of primarily 1-D parts.