COMPARING BRIGHTNESS CONSTANCY ASSUMPTION AND OPTIC FLOW EQUATION IN MOTION ESTIMATION ALGORITHMS

摘要

In the literature of computer vision and image processing, motion estimation and image registration problems are usually formulated as parametric fitting problems, solved using least squares-based techniques. The assumption that the grey level of all the pixels of a region remains constant between two consecutive images (brightness constancy assumption) can not be used directly using an ordinary least squares technique because its lack of linearity. The well-known solution of this problem derives the optic flow equation as linearized function to be minimized. Nevertheless, it is possible to directly use the brightness constancy assumption using a non-linear least squares-based estimator. The generalized least squares technique can be used in this context. In this paper two hierarchical least squares-based motion estimation algorithms are compared in order to demonstrate that the use of a generalized least squares estimator, and therefore the brightness constancy assumption, can produce more accurate results than the use of ordinary least squares-based estimator and the optic flow equation.