Hyperspectral image super-resolution based on attention ConvBiLSTM network

ABSTRACT

In this paper, a hyperspectral (HS) image super-resolution (SR) approach based on attention convolutional bi-long short-term memory (ConvBiLSTM) network is proposed, aiming to explore the collaborative spatial and spectral attention characteristics, thereby enhancing the spatial resolution of HS image. ConvBiLSTM network combines the spatial feature mining and sequential predicting abilities of convolutional neural network and recurrent neural network, respectively. We adapt the ConvBiLSTM network for our super-resolution purpose by regarding each band as a single frame of sequential data, and propose a band-sharing spatial-channel attention-combined ConvBiLSTM SR method to intensify the saliency features. Moreover, a spatial-regularized loss function is presented to further promote the fidelity of the super-resolved HS image. Experiments on four HS data sets show that the proposed approach outperforms some state-of-the-art HS image SR techniques, from the aspect of spectral fidelity.

KEYWORDS:

• Attention
• ConvBiLSTM
• convolution neural network
• hyperspectral image
• super-resolution

Acknowledgements

The authors would like to express their great appreciation to the Hyperspectral Image Analysis group and the NSF Funded Centre for Airborne Laser Mapping (NCALM) at the University of Houston; and to the IEEE GRSS Data Fusion Technical Committee for providing the CASI data. The authors would also like to sincerely thank the Jet Propulsion Laboratory of NASA for their publicly available AVIRIS data.

Disclosure statement

No potential conflict of interest was reported by the authors.

Data availability statement

Data available in a publicly accessible repository that does not issue DOIs Publicly available datasets were analysed in this study. Data can be found here: [http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes, accessed on 1 October 2021; http://www.grss-ieee.org/community/technical-committees/data-fusion/, accessed on 1 October 2021; http://aviris.jpl.nasa.gov, accessed on 1 October 2021].

Additional information

Funding

This work was supported by the Natural Science Foundation of Shanghai, China under Grant 19ZR1453800; National Natural Science Foundation of China under Grant 61901104; and Fundamental Research Funds for the Central Universities, China, under Grant 2232021D-33