Header logo is ps

Mixture models for optical flow computation


Conference Paper


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.

Author(s): Jepson, A. and Black, M.
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-93
Pages: 760-761
Year: 1993
Month: June

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: New York, NY

Links: pdf
tech report


  title = {Mixture models for optical flow computation},
  author = {Jepson, A. and Black, M.},
  booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-93},
  pages = {760-761},
  address = {New York, NY},
  month = jun,
  year = {1993},
  month_numeric = {6}