Dilated projection correction network based on autoencoder for hyperspectral image super-resolution. (February 2022)

• Record Type: Journal Article
• Authors: Wang, Xinya; Ma, Jiayi; Jiang, Junjun; Zhang, Xiao-Ping
• Is Part Of: Neural networks. Volume 146(2022)
• Page Start: 107
• Page End: 119
• Publication Date: 2022-02
• Subjects: Hyperspectral image -- Super-resolution -- Deep learning -- Autoencoder; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.11.014
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: This paper focuses on improving the spatial resolution of the hyperspectral image (HSI) by taking the prior information into consideration. In recent years, single HSI super-resolution methods based on deep learning have achieved good performance. However, most of them only simply apply general image super-resolution deep networks to hyperspectral data, thus ignoring some specific characteristics of hyperspectral data itself. In order to make full use of spectral information of the HSI, we transform the HSI SR problem from the image domain into the abundance domain by the dilated projection correction network with an autoencoder, termed as aeDPCN . In particular, we first encode the low-resolution HSI to abundance representation and preserve the spectral information in the decoder network, which could largely reduce the computational complexity. Then, to enhance the spatial resolution of the abundance embedding, we super-resolve the embedding in a coarse-to-fine manner by the dilated projection correction network where the back-projection strategy is introduced to further eliminate spectral distortion. Finally, the predictive images are derived by the same decoder, which increases the stability of our method, even at a large upscaling factor. Extensive experiments on real hyperspectral image scenes demonstrate the superiority of our method over the state-of-the-art, in terms of accuracy and efficiency. Highlights: We transform the single HSI SR problem into the abundance domain. We deploy a dilated projection network to improve the spatial resolution of abundance. We introduce a back-projection correction strategy to reduce the spectral distortion. Our light-weight model can attain comparable results on Pavia and Chikusei datasets.