A planar perspective image matching using point correspondences and rectangle-to-quadrilateral mapping

Abstract

In this paper, we consider a planar perspective transformation between images with overlapping region. It is based on the rectangle-to-quadrilateral mapping and normalized correlations. Initially, the global translation is determined by using a block matching, and to find the correspondence points maximizing correlation in the overlapping region by the perspective transformation, we use the simulated annealing (SA) algorithm based on the normalized correlation. In the block matching and SA, we use the Gaussian pyramid structure. We show the results of applying our proposed algorithm to mosaic images.