Reconstruction of non-rigid 3D shapes from stereo-motion
Pattern Recognition Letters
| Hi-index | 0.00 |
Recovering three-dimensional (3D) information of a scene from its images is a fundamental problem in computer vision. There exists two major multi-ocular cues for it, namely the motion cue and the stereo cue. This paper presents a new approach of integrating the two cues when two cameras that move through the scene while taking pictures repeatedly are available. The approach is based on the Singular Value Decomposition (SVD) technique, with which the 3D structure of the scene, the image projection parameters, the motion parameters, and the stereo geometry are all separated. The approach offers the advantages of both cues: simple correspondence as well as accurate reconstruction. It can also work with relatively short image sequences.