ML Anthology

A Bayesian Framework for Radar Shape-from-Shading

Adrian G. Bors, Edwin R. Hancock, Richard C. Wilson
CVPR 2000 pp. 1262-1268
doi:10.1109/CVPR.2000.855828 /cvpr/2000/bors2000cvpr-bayesian/

Abstract

This paper introduces a Bayesian approach to shape-from-shading (SFS) which is applied to terrain recovery in synthetic aperture radar (SAR) images. The Bayesian model relates the recovery of 3-D shape information to the original 3-D radar intensity and to edges separating different topographic regions. First, we model the image amplitude distribution and the reflection function in SAR images. Using a maximum log-likelihood feature detector derived from the image statistics we identify the ridges and ravines in the terrain image. These topographic features are used to constrain the recovery of surface normals in the shape-from-shading process. Finally, the surface normals are smoothed using robust statistics operators.

CVPR Semantic Scholar

Cite

Text

Bors et al. "A Bayesian Framework for Radar Shape-from-Shading." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855828

Markdown

[Bors et al. "A Bayesian Framework for Radar Shape-from-Shading." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/bors2000cvpr-bayesian/) doi:10.1109/CVPR.2000.855828

BibTeX

@inproceedings{bors2000cvpr-bayesian,
  title     = {{A Bayesian Framework for Radar Shape-from-Shading}},
  author    = {Bors, Adrian G. and Hancock, Edwin R. and Wilson, Richard C.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1262-1268},
  doi       = {10.1109/CVPR.2000.855828},
  url       = {https://mlanthology.org/cvpr/2000/bors2000cvpr-bayesian/}
}