Abstract
Fusing a low-resolution hyperspectral (LRHS) image and a high-resolution multispectral (HRMS) image to generate a high-resolution hyperspectral (HRHS) image has grown a significant and attractive application in remote sensing fields. Recently, the popularization of deep learning has injected more possibilities into the fusion work. However, there still exists a difficulty that is how to make the best of the acquired LRHS and HRMS images. In this article, we present a twice optimizing net with matrix decomposition to fulfill the fusion task, which can be roughly divided into three stages: pre-optimization, deep prior learning, post-optimization. Specifically, we first transform this fusion problem into a spectral optimization problem and a spatial optimization problem with the help of matrix decomposition. These two optimization problems can be handled sequentially by solving a linear equation, respectively, and then we can obtain the initial HRHS image by multiplying the two solutions. Next, we establish the mapping between the initial image and the reference image through an end-to-end deep residual network based on local and nonlocal connectivity. In order to get better performance, we have customized a loss function specifically for the fusion task as well. Finally, we return the predicted result again to the optimization procedure to get the final fusion image. After the evaluation on three simulated datasets and one real dataset, it illustrates that the proposed method outperforms many state-of-the-art ones.
Highlights
H YPERSPECTRAL images (HSIs) with hundreds of bands, which contain sufficient spectral characteristics are widely used in many remote sensing fields [1]–[8], such as military surveillance, farming, geographic information monitoring and weather report
In order to demonstrate the robustness of our method to noise and further verify its effectiveness when facing noise environment, we add Guassian white noise with different levels to the low-resolution hyperspectral (LRHS) images and the high-resolution multispectral (HRMS) images
To distinguish the spatial resolution of the LRHS images and the HRMS images, we intentionally set the decibel difference of the noise added to these two images as 10
Summary
H YPERSPECTRAL images (HSIs) with hundreds of bands, which contain sufficient spectral characteristics are widely used in many remote sensing fields [1]–[8], such as military surveillance, farming, geographic information monitoring and weather report. In order to do analysis more precisely and make decisions more appropriately, HSIs had better posses resolution as high as possible. While owing to the deficiencies of current satellite sensors, it seems impossible to acquire highresolution hyperspectral (HRHS) images directly. Manuscript received May 1, 2020; revised June 23, 2020; accepted July 10, 2020. Date of publication July 15, 2020; date of current version July 27, 2020.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
