Abstract

Abstract The computation of optical ow relies on merging information available over an image patch to form an estimate of 2D image velocity a t a p o i n t. This merging process raises a host of issues, which include the treatment of outliers in component v elocity measurements and the modeling of multiple motions within a patch which arise from occlusion boundaries or transparency. W e present a new approach which allows us to deal with these issues within a common framework. Our approach is based on the use of a probabilistic mixture m o del to explicitly represent m ultiple motions within a patch. We use a simple extension of the EM-algorithm to compute a maximum likelihood estimate for the various motion parameters. Preliminary experiments indicate that this approach is computationally e cient and can provide robust estimates of the optical ow v alues in the presence of outliers and multiple motions. The basic approach can also be applied to other problems in computational vision, such as the computation of 3D relative motion, which require the integration of several partial constraints to obtain a desired quantity.