1 May 2014 New intensity-hue-saturation pan-sharpening method based on texture analysis and genetic algorithm-adaption
Author Affiliations +
Pansharpening aims to fuse a low-resolution multispectral image with a high-resolution panchromatic image to create a multispectral image with high spatial and spectral resolution. The intensity-hue-saturation (IHS) fusion method transforms an image from RGB space to IHS space. This paper reports a method to improve the spectral resolution of a final multispectral image. The proposed method implies two modifications on the basic IHS method to improve the sharpness of the final image. First, the paper proposes a method based on a genetic algorithm to find the weight of each band of multispectral image in the fusion process. Later on, a texture-based technique is proposed to save the spectral information of the final image with respect to the texture boundaries. Spectral quality metrics in terms of SAM, SID, Q-average, RASE, RMSE, CC, ERGAS and UIQI are used in our experiments. Experimental results on IKONOS and QuickBird data show that the proposed method is more efficient than the original IHS-based fusion approach and some of its extensions, such as IKONOS IHS, edge-adaptive IHS and explicit band coefficient IHS, in preserving spectral information of multispectral images.
© 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
Rasoul Masoudi, Rasoul Masoudi, Peyman Kabiri, Peyman Kabiri, } "New intensity-hue-saturation pan-sharpening method based on texture analysis and genetic algorithm-adaption," Journal of Applied Remote Sensing 8(1), 083640 (1 May 2014). https://doi.org/10.1117/1.JRS.8.083640 . Submission:


Back to Top