Stereo and motion correspondence in a sequence of stereo images

摘要

In this paper, an approach with combined stereo and motion analysis to establish correspondences in a sequence of stereo images is outlined. The advantages of the presented approach are (1) in both the motion and stereo estimation no restriction on rigid and/or planar objects is assumed; (2) by introducing the image pyramid in the matching process — pyramid quided edge-point matching for motion estimation and multi-resolutional dynamic programming for disparity estimation — large motion and disparity vectors can be computed easily; (3) in order to exclude ambiguities with the dynamic programming, the cost function takes the interline, interframe and multi-resolutional spatial information into account. Both the algorithms for the stereo and motion estimation are presented here, together with some experimental results on images obtained from natural scenes containing motion.