Multimodal remote sensing image registration based on cross-cumulative residual entropy and NSCT

Image registration is widely used in remote sensing image processing. On one hand, non-subsamded Contourlet transform (NSCT) has the advantage of decomposing image in a flexible way;on the other hand, cross-cumulative residual entropy (CCRE) is effective in remote sensing image registration. Considering that, we propose a multimodal remote sensing image registration method which is based on cross-cumulative residual entropy and NSCT algorithm. First, the reference image and target image are decomposed with NSCT to obtain low frequency images, and then the cross-cumulative residual entropy of the obtained low frequency images is calculated. Set the cross-cumulative residual entropy as a similarity measurement. Secondly, Newton's method is employed to gain optimal parameters of the affine transformation model. Finally, the image registration is obtained with the optimal parameters. To validate our algorithm, we test two remote sensing images with our method. Simulation results show that the proposed method is able to find the global optimum rapidly and prevent dropping into a local minimum. In general, it is not only a fast and effective multimodal remote sensing image registration algorithm but also the one with high registration accuracy.