ML Anthology

Clear Underwater Vision

Yoav Y. Schechner, Nir Karpel
CVPR 2004 pp. 536-543
doi:10.1109/CVPR.2004.59 /cvpr/2004/schechner2004cvpr-clear/

Abstract

Underwater imaging is important for scientific research and technology, as well as for popular activities. We present a computer vision approach which easily removes degradation effects in underwater vision. We analyze the physical effects of visibility degradation. We show that the main degradation effects can be associated with partial polarization of light. We therefore present an algorithm which inverts the image formation process, to recover a good visibility image of the object. The algorithm is based on a couple of images taken through a polarizer at different orientations. As a by product, a distance map of the scene is derived as well. We successfully used our approach when experimenting in the sea using a system we built. We obtained great improvement of scene contrast and color correction, and nearly doubled the underwater visibility range.

PDF CVPR Semantic Scholar

Cite

Text

Schechner and Karpel. "Clear Underwater Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.59

Markdown

[Schechner and Karpel. "Clear Underwater Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/schechner2004cvpr-clear/) doi:10.1109/CVPR.2004.59

BibTeX

@inproceedings{schechner2004cvpr-clear,
  title     = {{Clear Underwater Vision}},
  author    = {Schechner, Yoav Y. and Karpel, Nir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {536-543},
  doi       = {10.1109/CVPR.2004.59},
  url       = {https://mlanthology.org/cvpr/2004/schechner2004cvpr-clear/}
}