Pansharpening by Complementing Compressed Sensing with Spectral Correction

Abstract

Pansharpening (PS) is a process used to generate high-resolution multispectral (MS) images from high-spatial-resolution panchromatic (PAN) and high-spectral-resolution multispectral images. In this paper, we propose a method for pansharpening by focusing on a compressed sensing (CS) technique. The spectral reproducibility of the CS technique is high due to its image reproducibility, but the reproduced image is blurry. Although methods of complementing this incomplete reproduction have been proposed, it is known that the existing method may cause ringing artifacts. On the other hand, component substitution is another technique used for pansharpening. It is expected that the spatial resolution of the images generated by this technique will be as high as that of the high-resolution PAN image, because the technique uses the corrected intensity calculated from the PAN image. Based on these facts, the proposed method fuses the intensity obtained by the component substitution method and the intensity obtained by the CS technique to move the spatial resolution of the reproduced image close to that of the PAN image while reducing the spectral distortion. Experimental results showed that the proposed method can reduce spectral distortion and maintain spatial resolution better than the existing methods.

Remote Sensing Image Fusion Algorithm Based on Two-Stream Fusion Network and Residual Channel Attention Mechanism

“…The popular algorithms are IHS (Intensity Hue Saturation) transformation [11], Principal component analysis (Principal Component Analysis) [12], Brovey transform (Brovey) [13], and so on. The fusion algorithm based on the component substitution has high computational efficiency, but it prones to the spectral distortion [14].…”