Next Article in Journal
Remote Sensing of Ecosystem Structure—Part 2: Initial Findings of Ecosystem Functioning through Intra- and Inter-Annual Comparisons with Earth Observation Data
Next Article in Special Issue
Neighboring Discriminant Component Analysis for Asteroid Spectrum Classification
Previous Article in Journal
Sea Surface Salinity and Wind Speed Retrievals Using GNSS-R and L-Band Microwave Radiometry Data from FMPL-2 Onboard the FSSCat Mission
Previous Article in Special Issue
A Novel Change Detection Approach Based on Spectral Unmixing from Stacked Multitemporal Remote Sensing Images with a Variability of Endmembers
Article

Hyperspectral and Multispectral Image Fusion by Deep Neural Network in a Self-Supervised Manner

by 1, 1,* and 2
1
School of Geodesy and Geomatics, Wuhan University, Wuhan 430072, China
2
School of Resource and Environmental Sciences, Wuhan University, Wuhan 430072, China
*
Author to whom correspondence should be addressed.
Academic Editors: Liangpei Zhang, Lefei Zhang, Qian Shi and Yanni Dong
Remote Sens. 2021, 13(16), 3226; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163226
Received: 18 July 2021 / Revised: 9 August 2021 / Accepted: 9 August 2021 / Published: 13 August 2021
(This article belongs to the Special Issue Recent Advances in Hyperspectral Image Processing)
Compared with multispectral sensors, hyperspectral sensors obtain images with high- spectral resolution at the cost of spatial resolution, which constrains the further and precise application of hyperspectral images. An intelligent idea to obtain high-resolution hyperspectral images is hyperspectral and multispectral image fusion. In recent years, many studies have found that deep learning-based fusion methods outperform the traditional fusion methods due to the strong non-linear fitting ability of convolution neural network. However, the function of deep learning-based methods heavily depends on the size and quality of training dataset, constraining the application of deep learning under the situation where training dataset is not available or of low quality. In this paper, we introduce a novel fusion method, which operates in a self-supervised manner, to the task of hyperspectral and multispectral image fusion without training datasets. Our method proposes two constraints constructed by low-resolution hyperspectral images and fake high-resolution hyperspectral images obtained from a simple diffusion method. Several simulation and real-data experiments are conducted with several popular remote sensing hyperspectral data under the condition where training datasets are unavailable. Quantitative and qualitative results indicate that the proposed method outperforms those traditional methods by a large extent. View Full-Text
Keywords: deep neural network; hyperspectral and multispectral fusion; self-supervised optimization deep neural network; hyperspectral and multispectral fusion; self-supervised optimization
Show Figures

Graphical abstract

MDPI and ACS Style

Gao, J.; Li, J.; Jiang, M. Hyperspectral and Multispectral Image Fusion by Deep Neural Network in a Self-Supervised Manner. Remote Sens. 2021, 13, 3226. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163226

AMA Style

Gao J, Li J, Jiang M. Hyperspectral and Multispectral Image Fusion by Deep Neural Network in a Self-Supervised Manner. Remote Sensing. 2021; 13(16):3226. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163226

Chicago/Turabian Style

Gao, Jianhao, Jie Li, and Menghui Jiang. 2021. "Hyperspectral and Multispectral Image Fusion by Deep Neural Network in a Self-Supervised Manner" Remote Sensing 13, no. 16: 3226. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163226

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop