Genetic algorithms (GAs) are known to be robust for search and optimization
problems. Image registration can take advantage of the robustness of GAs i
n finding best transformation between two images, of the same location with
slightly different orientation, produced by moving spaceborne remote sensi
ng instruments. In this paper, we present 2-phase sequential and coarse-gra
ined parallel image registration algorithms using GAs as optimization mecha
nism. In its first phase, the algorithm finds a small set of goad solutions
using low-resolution Versions of the images. Based on these candidate low-
resolution solutions, the algorithm uses the full resolution image data to
refine the final registration results in the second phase. Experimental res
ults are presented and revealed that our algorithms yield very accurate reg
istration results for LandSat Thematic Mapper images, and the parallel algo
rithm scales quite well on the Beowulf parallel cluster. (C) 2001 Elsevier
Science B.V. All rights reserved.