UDC 621.397.7
COMPARATIVE ANALYSIS OF ALGORITHMS FOR MULTISPECTRAL IMAGE FUSION
V. T. Dmitriev, Ph.D. (Tech.), head of department, RSREU, Ryazan, Russia;
orcid.org/0000-0001-5521-6886, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
P. N. Skonnikov, post-graduate student, RSREU, Ryazan, Russia;
orcid.org/0000-0002-4989-3757, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The article shows the relevance of the problem for multispectral image fusion during search and rescue
operations. Well-known algorithms for such image fusion are considered and implemented. Based on the
publicly available datasets of multispectral images a combined database including 496 pairs of images has
been compiled to compare the algorithms considered. The results of image fusion using the considered algorithms
are obtained. The aim is to compare the known algorithms for multispectral image in terms of objective
quality indices. Comparison of fusion results was carried out by two criteria: Piella metric and combined
quality index. Based on the results of the comparison, it was concluded that the best values of combined
quality index for multispectral image fusion are provided by the algorithms based on local weighted
summation, principal components analysis and Laplace pyramid.
Key words: multispectral image fusion, local weighted summation, infrared range, objective quality index,Piella metric, image dataset, enhanced vision, rescue operations.