Model Driven Segmentation of Articulating Humans in Laplacian Eigenspace

TitleModel Driven Segmentation of Articulating Humans in Laplacian Eigenspace
Publication TypeJournal Articles
Year of Publication2008
AuthorsSundaresan A, Chellappa R
JournalPattern Analysis and Machine Intelligence, IEEE Transactions on
Pagination1771 - 1785
Date Published2008/10//
ISBN Number0162-8828
Keywords3D voxel data segmentation, algorithms, Anatomic;Pattern Recognition, Artificial intelligence, Automated;Reproducibility of Results;Sensitivity and Specificity;Whole Body Imaging;, Computer simulation, Computer-Assisted;Imaging, curve fitting, Eigenvalues and eigenfunctions, graph theory, human articulation, human body graphical model, human motion analysis, HUMANS, Image Enhancement, Image Interpretation, Image motion analysis, image registration, Image segmentation, Laplace transforms, Laplacian eigenspace transform, model driven segmentation, probability, representative graph, skeleton registration, Smoothing methods, solid modelling, spline fitting error, splines (mathematics), Three-Dimensional;Joints;Models, top-down probabilistic approach, voxel neighborhood graph

We propose a general approach using Laplacian Eigenmaps and a graphical model of the human body to segment 3D voxel data of humans into different articulated chains. In the bottom-up stage, the voxels are transformed into a high-dimensional (6D or less) Laplacian Eigenspace (LE) of the voxel neighborhood graph. We show that LE is effective at mapping voxels on long articulated chains to nodes on smooth 1D curves that can be easily discriminated, and prove these properties using representative graphs. We fit 1D splines to voxels belonging to different articulated chains such as the limbs, head and trunk, and determine the boundary between splines using the spline fitting error. A top-down probabilistic approach is then used to register the segmented chains, utilizing their mutual connectivity and individual properties. Our approach enables us to deal with complex poses such as those where the limbs form loops. We use the segmentation results to automatically estimate the human body models. While we use human subjects in our experiments, the method is fairly general and can be applied to voxel-based segmentation of any articulated object composed of long chains. We present results on real and synthetic data that illustrate the usefulness of this approach.