Time-space segmentation and motion estimation based on higher order statistics

Publisher Website
Google Scholar
Abstract
The paper illustrates a comprehensive method for the motion compensation to be used in predictive video coding. The method is based on the observation that structured artifacts as those consisting of isolated points, lines, edges, organized textures are directly perceived by the user, while artifacts resembling realizations of gaussian processes can be considered less important. A fidelity criterion based on the Mean Forth-Cumulant as indirect estimate of the local entropy level is then applied to drive both the segmentation and the motion estimation phases. The motion estimator is conceptually similar to the higher order moments techniques employed in time delay estimation, and takes advantage of the Gaussian signals rejection capability, typical of the higher order cumulants. The contribution describes the theoretical framework of cumulant based motion estimation. The performance of a coder based on the discrimination of the temporal activity by means of cumulants, is illustrated through experimental data.

This publication has 0 references indexed in Scilit: