Remote sensing images data fusion: A wavelet transform approach for urban analysis

There are several situations that simultaneously require both high spatial and spectral resolution in a single image. In literature a certain number of methods have been proposed to merge panchromatic and multispectral data. Classical processes involve a simple linear transformation of the combined data spaces (Brovey, HSV, PCA). However standard data fusion methods may not be satisfactory to merge a high-resolution panchromatic image and a low-resolution multispectral image because they distort the spectral characteristics of the original multispectral data. It has been showed that an image fusion technique based on Multiresolution Wavelet Decomposition (MWD) seems to be a better trade-off between spectral and spatial information. In this paper, we develop some techniques, based on MWD, for the data fusion of such images. The methods presented for reducing the fusion imperfections doesn't consist simply of replacing some wavelet coefficients of the multispectral image by the corresponding coefficients of the high-resolution image but tend to carry out, a real integration between two pyramidal decomposition. In fact, it is possible to fuse the wavelet coefficients of two decompositions in each scale level and with some appropriate rules. Moreover, some "ad hoc" algorithms have been implemented to correct spectral distortions in the synthesized high resolution multispectral image. We tested the methods to merge IKONOS panchromatic (1m spatial resolution) and IKONOS multispectral (4m spatial resolution) images in urban areas. The techniques presented are clearly better than classical fusion methods in preserving both spectral and spatial information on urban areas.