Compressed sensing based remote sensing image reconstruction via employing similarities of reference images

In the traditional reconstruction algorithm for compressed sensing, we use the measurement matrix and the corresponding observed image to recover the target image. In the application of remote sensing, there are many multi-source and multi-temporal reference images that have similar information to that of the target image. In this paper, we propose an algorithm to reconstruct the target image with information from multi-source and multi-temporal reference images to improve the image reconstruction accuracy, in other words, to improve the degree of similarity between the reconstructed image and the target image. The basic principle of our method is to construct a penalty term with the similarity of the target sparse coefficient and the reference sparse coefficient to constrain the reconstruction process. The experimental results demonstrate the effectiveness of our method.