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.<>
Mixture models for optical flow computation
01.01.1993
180094 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multispectral constraints for optical flow computation
IEEE | 1990
|Diffusion constructs in optical flow computation
British Library Online Contents | 2005
|Superpipelined high-performance optical-flow computation architecture
British Library Online Contents | 2008
|Optical flow modeling and computation: A survey
British Library Online Contents | 2015
|Salient Feature Detection for optical flow computation
IEEE | 2016
|