Motion Segmentation for 3D Video Based on Spherical Registration

In this paper, a highly accurate motion segmentation technique for 3D video is presented. In conventional approaches, motion of the objects was analyzed using shape feature vectors extracted 3D video frames. This was because it was very difficult to locate and track feature points in the objects in the 3D space due to that fact that the number of vertices and connection vary each frame. In this study, we developed an algorithm to analyze the objects´ motion in the 3D space using the spherical registration based on the iterated closest point algorithm. Rough motion tracking is conducted and the degree of motion is robustly calculated by this method. Although the approach is straightforward, much better motion segmentation results than the conventional approaches are obtained by yielding such high precision and recall rates as 95% and 92% on average.