Fusion of remote sensing images based on Principal Component Analysis and Nonsubsampled Contourlet Transform

Abstract

A novel fusion method is proposed for multispectral (MS) and panchromatic (PAN) satellite images using Principal Component Analysis (PCA) and Nonsubsampled Contourlet Transform (NSCT). This method first performs PCA on MS, and NSCT on PAN and the first principal component (PC1) to get corresponding low-frequency and high-frequency coefficients, then fuses the approximation coefficients using PCA again for the tradeoff between the spectral and spatial information, and fuses the subbands coefficients based on Universal Image Qualigy Index (UIQI) and local sobel gradient for the spatial detail information, finally a fused image is formed through inverse NSCT and inverse PCA. Experimental results show that the proposed fusion method can effectively preserve spectral information while improving the spatial quality, and outperforms the general IHS-, PCA-, wavelet-, contourlet-based fusion methods.