ML Anthology

Recovering LSHGCs and SHGCs from Stereo

Ronald C.-K. Chung, Ramakant Nevatia
CVPR 1992 pp. 42-48
doi:10.1109/CVPR.1992.223229 /cvpr/1992/chung1992cvpr-recovering/

Abstract

The problem of computing volumetric shape from stereo is examined. It is argued that intermediate two-and-one-half-dimensional dense or wire-frame descriptions may not be always possible from stereo, especially when there are curved surfaces in the scene, and that 3D volumetric descriptions of objects may have to be derived directly from stereo correspondences. Methods are then presented for recovering volumetric shape with linear straight homogeneous generalized cones (LSHGCs) and straight homogeneous generalized cones (SHGCs) as the shape models, using some invariant properties in their monocular and stereo projections. Experimental results on images of objects with curved surfaces are given.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Chung and Nevatia. "Recovering LSHGCs and SHGCs from Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223229

Markdown

[Chung and Nevatia. "Recovering LSHGCs and SHGCs from Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/chung1992cvpr-recovering/) doi:10.1109/CVPR.1992.223229

BibTeX

@inproceedings{chung1992cvpr-recovering,
  title     = {{Recovering LSHGCs and SHGCs from Stereo}},
  author    = {Chung, Ronald C.-K. and Nevatia, Ramakant},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {42-48},
  doi       = {10.1109/CVPR.1992.223229},
  url       = {https://mlanthology.org/cvpr/1992/chung1992cvpr-recovering/}
}