Multi-Stage Unsupervised Learning for Multi-Body Motion Segmentation

This paper proposes a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions, which enables us to not only separate simple motions that the authors frequently encounter with high precision but also preserve the high performance for considerably general 3D motions.

Abstract

Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions, but objects in the scene are usually assumed to undergo general 3-D motions. As a result, the segmentation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we propose a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions and show by simulated and real video experiments that the segmentation accuracy significantly improves without compromising the accuracy for general 3-D motions.