Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network
Super-resolution (SR) technology has emerged as an effective tool for image analysis and interpretation. However, single hyperspectral (HS) image SR remains challenging, due to the high spectral dimensionality and lack of available high-resolution information of auxiliary sources. To fully exploit t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/20/4074 |
| _version_ | 1797513212434841600 |
|---|---|
| author | Xiaochen Lu Dezheng Yang Junping Zhang Fengde Jia |
| author_facet | Xiaochen Lu Dezheng Yang Junping Zhang Fengde Jia |
| author_sort | Xiaochen Lu |
| collection | DOAJ |
| description | Super-resolution (SR) technology has emerged as an effective tool for image analysis and interpretation. However, single hyperspectral (HS) image SR remains challenging, due to the high spectral dimensionality and lack of available high-resolution information of auxiliary sources. To fully exploit the spectral and spatial characteristics, in this paper, a novel single HS image SR approach is proposed based on a spatial correlation-regularized unmixing convolutional neural network (CNN). The proposed approach takes advantage of a CNN to explore the collaborative spatial and spectral information of an HS image and infer the high-resolution abundance maps, thereby reconstructing the anticipated high-resolution HS image via the linear spectral mixture model. Moreover, a dual-branch architecture network and spatial spread transform function are employed to characterize the spatial correlation between the high- and low-resolution HS images, aiming at promoting the fidelity of the super-resolved image. Experiments on three public remote sensing HS images demonstrate the feasibility and superiority in terms of spectral fidelity, compared with some state-of-the-art HS image super-resolution methods. |
| first_indexed | 2024-03-10T06:14:27Z |
| format | Article |
| id | doaj.art-8d60eba8f668425a8c3d23acb7e4cd08 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T06:14:27Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8d60eba8f668425a8c3d23acb7e4cd082023-11-22T19:53:46ZengMDPI AGRemote Sensing2072-42922021-10-011320407410.3390/rs13204074Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural NetworkXiaochen Lu0Dezheng Yang1Junping Zhang2Fengde Jia3School of Information Science and Technology, Donghua University, Shanghai 201620, ChinaSchool of Information Science and Technology, Donghua University, Shanghai 201620, ChinaSchool of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Information Science and Technology, Donghua University, Shanghai 201620, ChinaSuper-resolution (SR) technology has emerged as an effective tool for image analysis and interpretation. However, single hyperspectral (HS) image SR remains challenging, due to the high spectral dimensionality and lack of available high-resolution information of auxiliary sources. To fully exploit the spectral and spatial characteristics, in this paper, a novel single HS image SR approach is proposed based on a spatial correlation-regularized unmixing convolutional neural network (CNN). The proposed approach takes advantage of a CNN to explore the collaborative spatial and spectral information of an HS image and infer the high-resolution abundance maps, thereby reconstructing the anticipated high-resolution HS image via the linear spectral mixture model. Moreover, a dual-branch architecture network and spatial spread transform function are employed to characterize the spatial correlation between the high- and low-resolution HS images, aiming at promoting the fidelity of the super-resolved image. Experiments on three public remote sensing HS images demonstrate the feasibility and superiority in terms of spectral fidelity, compared with some state-of-the-art HS image super-resolution methods.https://www.mdpi.com/2072-4292/13/20/4074convolutional neural networkdeep learninghyperspectralsuper-resolutionunmixing |
| spellingShingle | Xiaochen Lu Dezheng Yang Junping Zhang Fengde Jia Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network Remote Sensing convolutional neural network deep learning hyperspectral super-resolution unmixing |
| title | Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network |
| title_full | Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network |
| title_fullStr | Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network |
| title_full_unstemmed | Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network |
| title_short | Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network |
| title_sort | hyperspectral image super resolution based on spatial correlation regularized unmixing convolutional neural network |
| topic | convolutional neural network deep learning hyperspectral super-resolution unmixing |
| url | https://www.mdpi.com/2072-4292/13/20/4074 |
| work_keys_str_mv | AT xiaochenlu hyperspectralimagesuperresolutionbasedonspatialcorrelationregularizedunmixingconvolutionalneuralnetwork AT dezhengyang hyperspectralimagesuperresolutionbasedonspatialcorrelationregularizedunmixingconvolutionalneuralnetwork AT junpingzhang hyperspectralimagesuperresolutionbasedonspatialcorrelationregularizedunmixingconvolutionalneuralnetwork AT fengdejia hyperspectralimagesuperresolutionbasedonspatialcorrelationregularizedunmixingconvolutionalneuralnetwork |