Computer Vision Laboratory, Computer Science Center, University of Maryland, College Park, MD 20742, U.S.A.
Abstract:
A new algorithm for estimating motion from image sequences is presented. Initial motion estimates are determined based on a least-squares solution to a set of independent linear constraints on the motion at a pixel. These initial estimates are then improved by a nonlinear smoothing operation. The results of this algorithm are compared with those obtained by the Horn-Schunck algorithm on a number of image sequences.