Urban remote image fusion using fuzzy rules

A pixel-level fusion approach is proposed to refine the resolution of urban multi-spectral images using the corresponding high-resolution panchromatic images. After the two images are decomposed by wavelet transform, three texture features are extracted from high-frequency detailed sub-images. Then a fuzzy fusion rule is used to merge wavelet coefficients from the two images according to the extracted features. Experimental results indicate that, comparing with the traditional methods, the proposed method can efficiently preserve the spectral information while improving the spatial resolution of the urban remote sensing images.