Lucas-Kanade 20 Years On: A Unifying Framework: Part 1

Abstract

Since the Lucas-Kanade algorithm was proposed in 1981 image alignment has become one of the most widely used techniques in computer vision. Applications range from optical flow and tracking to layered motion, mosaic-ing, and face coding. Numerous algorithms have been proposed and a wide variety of extensions have been made to the original formulation. We present an overview of image alignment, describing most of the algorithms and their extensions in a consistent framework. We concentrate on the inverse compositional algorithm, an efficient algorithm that we recently proposed. We examine which of the extensions to Lucas-Kanade can be used with the inverse compositional algorithm without any significant loss of efficiency, and which cannot. In this paper, Part 1 of a 2 part series, we cover the quantity approximated, the warp update rule, and the gradient descent approximation. In a future Part 2 of this 2 paper series we will cover the choice of the norm, how to allow linear appearance variation, how to impose priors on the parameters, and various heuristics to avoid local minima.