Spectral Methods for 3-D Motion Segmentation of Sparse Scene-Flow

The progress in the acquisition of 3-D data from multicamera set-ups has opened the way to a new way of loking at motion analysis. This paper proposes a solution to the motion segmentation in the context of sparse scene flow. In particular, our interest focuses on the disassociation of motions belonging to different rigid objects, starting from the 3-D trajectories of features lying on their surfaces. We analyze these trajectories and propose a representation suitable for defining robust-pairwise similarity measures between trajectories and handling missing data. The motion segmentation is treated as graph multi-cut problem, and solved with spectral clustering techniques (two algorithms are presented). Experiments are done over simulated and real data in the form of sparse scene-flow; we also evaluate the results on trajectories from motion capture data. A discussion is provided on the results for each algorithm, the parameters and the possible use of these results in motion analysis.