Random sampling algorithm in the image registration problem

O. N. Granichin, A. T. Vakhitov

St. Petersburg State University, Department of Mathematics and Mechanics

Abstract: Image registration is one of the basic problems of computer vision. It arises in optical flow estimation, stereo vision, and tracking problems. One of the classical approaches proposed by B. Lucas and T. Kanade is based on optimization of some cost function. In this article image registration algorithm based on Lucas–Kanade approach is proposed (random sampling algorithm). It shows high performance results.

Keywords: computer vision, Lucas–Kanade approach, optical flow, simultaneous perturbation stochastic approximation (SPSA).

UDC: 004.932.2