ML Anthology

Computing Optical Flow with Physical Models of Brightness Variation

Horst W. Haussecker, David J. Fleet
CVPR 2000 pp. 2760-2767
doi:10.1109/CVPR.2000.854951 /cvpr/2000/haussecker2000cvpr-computing/

Abstract

This paper exploits physical models of time-varying brightness in image sequences to estimate optical flow and physical parameters of the scene. Previous approaches handled violations of brightness constancy with the use of robust statistics or with generalized brightness constancy constraints that allow generic types of contrast and illumination changes. We consider models of brightness variation that have time-dependent physical causes, namely, changing surface orientation with respect to a directional illuminant, motion of the illuminant, and physical models of heat transport in infrared images. We simultaneously estimate the optical flow and the relevant physical parameters. The estimation problem is formulated using total least squares (TLS), with confidence bounds on the parameters.

PDF CVPR Semantic Scholar

Cite

Text

Haussecker and Fleet. "Computing Optical Flow with Physical Models of Brightness Variation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854951

Markdown

[Haussecker and Fleet. "Computing Optical Flow with Physical Models of Brightness Variation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/haussecker2000cvpr-computing/) doi:10.1109/CVPR.2000.854951

BibTeX

@inproceedings{haussecker2000cvpr-computing,
  title     = {{Computing Optical Flow with Physical Models of Brightness Variation}},
  author    = {Haussecker, Horst W. and Fleet, David J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {2760-2767},
  doi       = {10.1109/CVPR.2000.854951},
  url       = {https://mlanthology.org/cvpr/2000/haussecker2000cvpr-computing/}
}