Fusion of multispectral and panchromatic data using regionally weighted principal component analysis and wavelet

This study proposes a new multispectral (MS) and panchromatic (PAN) image fusion algorithm based on regionally weighted principal component analysis (RW-PCA) and wavelet. First, the MS images are segmented into spectrally similar regions based on the fuzzy c-means (FCM) clustering method. Secondly, based on the spectral vector's degree of membership in each region, a new RW-PCA method is proposed to fuse the MS and PAN images region by region, and fused MS images are obtained. In the traditional PCA-based fusion method, the MS and PAN images are fused globally with the same transform method. In the proposed RW-PCA-based fusion method, the local spectrum information of the MS images is employed, and the spectral information is better preserved in the fused MS images. Finally, in order to improve the quality of spectral and spatial details, the above fused MS images and the original PAN images are further fused using the wavelet-based fusion method, and the final fused MS images are obtained. Experimental results demonstrated that the proposed image fusion algorithm performs better in spectral preservation and spatial quality improvement than some other methods do.