ML Anthology

Mixture Models for Optical Flow Computation

Allan D. Jepson, Michael J. Black
CVPR 1993 pp. 760-761
doi:10.1109/CVPR.1993.341161 /cvpr/1993/jepson1993cvpr-mixture/

Abstract

The computation of optical flow relies on merging information available over an image patch to form an estimate of 2-D image velocity at a point. This merging process raises many issues. These include the treatment of outliers in component velocity measurements and the modeling of multiple motions within a patch which arise from occlusion boundaries or transparency. A new approach for dealing with these issues is presented. It is based on the use of a probabilistic mixture model to explicitly represent multiple motions within a patch. A simple extension of the EM-algorithm is used to compute a maximum likelihood estimate for the various motion parameters. Preliminary experiments indicate that this approach is computationally efficient, and that it can provide robust estimates of the optical flow values in the presence of outliers and multiple motions.< <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

Jepson and Black. "Mixture Models for Optical Flow Computation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341161

Markdown

[Jepson and Black. "Mixture Models for Optical Flow Computation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/jepson1993cvpr-mixture/) doi:10.1109/CVPR.1993.341161

BibTeX

@inproceedings{jepson1993cvpr-mixture,
  title     = {{Mixture Models for Optical Flow Computation}},
  author    = {Jepson, Allan D. and Black, Michael J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {760-761},
  doi       = {10.1109/CVPR.1993.341161},
  url       = {https://mlanthology.org/cvpr/1993/jepson1993cvpr-mixture/}
}