METHOD OF VIDEO CODING SHOULDER MOVEMENT FROM A SEQUENCE OF IMAGES

摘要

A method of video coding the movement of shoulders from a sequence of images comprising: coding the shoulder region from at least one of the images based, at least in part, on a limited number of selected feature points employing two-dimensional (2D) deformable mesh based coding; and estimating the movement of the shoulders in other images of the sequence using the 2D deformable mesh.