Improved registration method for infrared and visible remote sensing image using NSCT and SIFT

This paper introduces an improved image registration method for infrared and visible remote sensing image based on NSCT and SIFT algorithm. As the infrared and visible spectral characteristics of remote sensing images are inconsistent, the gray difference between these two images are quite distinct, so there are less matching points by using SIFT algorithm directly. The method of NSCT can decompose the image to a series of frequency channels and high frequency channels contain the edge details of the original image. It could get more matching points and improve the matching rate and the accuracy of registration by using SIFT registration method between two high frequency channels of decomposed images.