Abstract
Hyperspectral remote sensing images (HSIs) have a higher spectral resolution compared to multispectral remote sensing images, providing the possibility for more reasonable and effective analysis and processing of spectral data. However, rich spectral information usually comes at the expense of low spatial resolution owing to the physical limitations of sensors, which brings difficulties for identifying and analyzing targets in HSIs. In the super-resolution (SR) field, many methods have been focusing on the restoration of the spatial information while ignoring the spectral aspect. To better restore the spectral information in the HSI SR field, a novel super-resolution (SR) method was proposed in this study. Firstly, we innovatively used three-dimensional (3D) convolution based on SRGAN (Super-Resolution Generative Adversarial Network) structure to not only exploit the spatial features but also preserve spectral properties in the process of SR. Moreover, we used the attention mechanism to deal with the multiply features from the 3D convolution layers, and we enhanced the output of our model by improving the content of the generator’s loss function. The experimental results indicate that the 3DASRGAN (3D Attention-based Super-Resolution Generative Adversarial Network) is both visually quantitatively better than the comparison methods, which proves that the 3DASRGAN model can reconstruct high-resolution HSIs with high efficiency.
Highlights
A hyperspectral image (HSI) is a three-dimensional data cube that records a set of two-dimensional images, which represent the reflectance or radiance of a scene at various electromagnetic wavelengths [1]
To address the spectral-distortion problem, and to deal with the multiply feature produced by the network, we introduced the 3D convolution into SRGAN
We proposed a 3DASRGAN model for SR of HSIs by identifying the end-to-end full-band mapping between LR and HR HSIs
Summary
A hyperspectral image (HSI) is a three-dimensional data cube that records a set of two-dimensional images (or bands), which represent the reflectance or radiance of a scene at various electromagnetic wavelengths [1]. To reduce the proportion of noise in the collected information, a relatively large area of spectral information needs to be gathered together so it can be strong enough to be detected, which will trade off spatial resolution [5]. In these low-spatial-resolution images, it is very hard to utilize the spatial feature to identify objects on the ground with acceptable accuracy, which limits the applications of HSIs. In these low-spatial-resolution images, it is very hard to utilize the spatial feature to identify objects on the ground with acceptable accuracy, which limits the applications of HSIs In this case, how to reconstruct HSIs into high-resolution images is a significant task
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 callDisclaimer: 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.
