ML Anthology

Improved Motion Stereo Matching Based on a Modified Dynamic Programming

Mikhail G. Mozerov, Vitaly Kober, Tae-Sun Choi
CVPR 2000 pp. 2501-2505
doi:10.1109/CVPR.2000.854894 /cvpr/2000/mozerov2000cvpr-improved/

Abstract

A new method for computing precise depth map estimates of 3D shape of a moving object is proposed. 3D shape recovery in motion stereo is formulated as a matching optimization problem of multiple stereo images. The proposed method is a heuristic modification of dynamic programming applied to two-dimensional optimization problem. 3D shape recovery using real motion stereo images demonstrates a good performance of the algorithm in terms of reconstruction accuracy.

CVPR Semantic Scholar

Cite

Text

Mozerov et al. "Improved Motion Stereo Matching Based on a Modified Dynamic Programming." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854894

Markdown

[Mozerov et al. "Improved Motion Stereo Matching Based on a Modified Dynamic Programming." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/mozerov2000cvpr-improved/) doi:10.1109/CVPR.2000.854894

BibTeX

@inproceedings{mozerov2000cvpr-improved,
  title     = {{Improved Motion Stereo Matching Based on a Modified Dynamic Programming}},
  author    = {Mozerov, Mikhail G. and Kober, Vitaly and Choi, Tae-Sun},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {2501-2505},
  doi       = {10.1109/CVPR.2000.854894},
  url       = {https://mlanthology.org/cvpr/2000/mozerov2000cvpr-improved/}
}