Remote sensing image fusion based on wavelet-based contourlet packet

In this paper, an algorithm based on wavelet-based contourlet transform is proposed for remote sensing image fusion. This method mainly involves three steps: The first stage provides subband decomposition, which in the case of the WBCT is a wavelet transform, in contrast to the Laplacian pyramid used in contourlets. The second stage of the WBCT is a directional filter bank (DFB), decomposition of the coefficients on wavelet-based contourlet packets (WBCP) and selection of proper fusion criterion in the contourlet subband. The main merit of the proposed method is that the contourlet transform can provide optimally sparse representation of objects with singularities along C² edges and the wavelet-based contourlet packets (WBCP) can decompose the high frequency parts of the images which are not decomposed in discrete wavelet transform. This algorithm of fusing the images from different sensors can take advantage of the curves features of the source images more effectively. The experimental results demonstrate that this algorithm performs better than classical fusion methods both in visual effect and object evaluation.