ML Anthology

Stereo-Motion That Complements Stereo and Motion Analyses

Pui-Kuen Ho, Ronald Chung
CVPR 1997 pp. 213-218
doi:10.1109/CVPR.1997.609322 /cvpr/1997/ho1997cvpr-stereo/

Abstract

Recovering three-dimensional (3D) information of a scene from its images is a fundamental problem in computer vision. There exists two major multi-ocular cue 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.

CVPR Semantic Scholar

Cite

Text

Ho and Chung. "Stereo-Motion That Complements Stereo and Motion Analyses." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609322

Markdown

[Ho and Chung. "Stereo-Motion That Complements Stereo and Motion Analyses." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/ho1997cvpr-stereo/) doi:10.1109/CVPR.1997.609322

BibTeX

@inproceedings{ho1997cvpr-stereo,
  title     = {{Stereo-Motion That Complements Stereo and Motion Analyses}},
  author    = {Ho, Pui-Kuen and Chung, Ronald},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {213-218},
  doi       = {10.1109/CVPR.1997.609322},
  url       = {https://mlanthology.org/cvpr/1997/ho1997cvpr-stereo/}
}