Spectral-learning-based Transformer Network for the Spectral Super-resolution of Remote Sensing Degraded Images

• Published in: IEEE geoscience and remote sensing letters 2023-01, Vol.20, p.1-1
• Main Authors: Li, Zengyi, Li, Ligang, Liu, Bo, Cao, Yuan, Zhou, Wenbo, Ni, Wei, Yang, Zhen
• Format: Article
• Language: English
• Subjects: Atmospheric effects; Degradation; Feature extraction; Hyperspectral imaging; Image degradation; Image resolution; Learning; Mathematical models; Methods; Modules; Remote sensing; Root-mean-square errors; spectral super-resolution; spectral transformer; spectral-response function; Superresolution; Task analysis; Transformers
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2023.3287037

Hyperspectral images (HSIs) are widely used as data formats for remote sensing. Correspondingly, the spectral super-resolution (SSR) technique used to generate high-spatial-resolution HSIs from high-spatial-resolution remote sensing multispectral images (MSIs) has emerged as a popular research topic owing to its high costs and hardware requirements. Generally, existing SSR methods obtain an HSI from the MSI of natural scenes. However, these methods barely learn the complex spectra found in remote sensing images and lack effective treatments for the degradation phenomenon in remote sensing scenes. In this study, a spectral-learning-based transformer network composed of a spectral-response-function (SRF)-guided multilevel feature extraction module (MFEM) and spectral nonlinear mapping learning module (NMLM) is cascaded. The NMLM uses different blocks to gradually learn spatial and spectral information from remote sensing images. Additionally, we focus on atmospheric effects and other factors that influence the generation of remote sensing images and design an MFEM to eliminate these effects. To augment the spectral dimension, an SRF is precisely added to the MFEM as a guide. Experimental results on the Obita Hyperspectral Satellites, Pavia Center, and Washington DC Mall datasets reveal that our method outperforms other state-of-the-art methods in terms of the root mean square error, mean relative absolute error, and relative root mean square error.