Region-Based Motion Analysis and 3D Reconstruction for a Translational Video Sequence

Abstract

This paper presents a hybrid 1D motion estimation algorithm which combines pixel-based and region-based approaches that can give depth images from translational video sequences with very high quality. Firstly, we combine the motion information estimated by a variational regularization approach and by the Gabor transform through histogram analysis to identify those regions with zero motion (like for the sky). Then another round of region matching is carried out to refine the motion values for the other regions. Our algorithm can detect most of the sky regions segmented by foreground objects with complex geometry while keeping the boundaries of moving objects sharp and clear, which is an very important feature to obtain accurate 3D models. The high quality motion maps/depth images obtained by our algorithm are shown along with 3D reconstructions from novel viewpoints.