Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network
Existing hyperspectral sensors usually produce high-spectral-resolution but low-spatial-resolution images, and super-resolution has yielded impressive results in improving the resolution of the hyperspectral images (HSIs). However, most of the super-resolution methods require multiple observations o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/10/12/1939 |
| _version_ | 1818960372569210880 |
|---|---|
| author | Zhi He Lin Liu |
| author_facet | Zhi He Lin Liu |
| author_sort | Zhi He |
| collection | DOAJ |
| description | Existing hyperspectral sensors usually produce high-spectral-resolution but low-spatial-resolution images, and super-resolution has yielded impressive results in improving the resolution of the hyperspectral images (HSIs). However, most of the super-resolution methods require multiple observations of the same scene and improve the spatial resolution without fully considering the spectral information. In this paper, we propose an HSI super-resolution method inspired by the deep Laplacian pyramid network (LPN). First, the spatial resolution is enhanced by an LPN, which can exploit the knowledge from natural images without using any auxiliary observations. The LPN progressively reconstructs the high-spatial-resolution images in a coarse-to-fine fashion by using multiple pyramid levels. Second, spectral characteristics between the low- and high-resolution HSIs are studied by the non-negative dictionary learning (NDL), which is proposed to learn the common dictionary with non-negative constraints. The super-resolution results can finally be obtained by multiplying the learned dictionary and its corresponding sparse codes. Experimental results on three hyperspectral datasets demonstrate the feasibility of the proposed method in enhancing the spatial resolution of the HSI with preserving the spectral information simultaneously. |
| first_indexed | 2024-12-20T11:56:29Z |
| format | Article |
| id | doaj.art-b7200dcfd90a4cfbbc055418ebde853c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T11:56:29Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b7200dcfd90a4cfbbc055418ebde853c2022-12-21T19:41:38ZengMDPI AGRemote Sensing2072-42922018-12-011012193910.3390/rs10121939rs10121939Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid NetworkZhi He0Lin Liu1Guangdong Provincial Key Laboratory of Urbanization and Geo-Simulation, Center of Integrated Geographic Information Analysis, School of Geography and Planning, Sun Yat-Sen University, Guangzhou 510275, ChinaCenter of Geographic Information Analysis for Public Security, School of Geographic Sciences, Guangzhou University, Guangzhou 510275, ChinaExisting hyperspectral sensors usually produce high-spectral-resolution but low-spatial-resolution images, and super-resolution has yielded impressive results in improving the resolution of the hyperspectral images (HSIs). However, most of the super-resolution methods require multiple observations of the same scene and improve the spatial resolution without fully considering the spectral information. In this paper, we propose an HSI super-resolution method inspired by the deep Laplacian pyramid network (LPN). First, the spatial resolution is enhanced by an LPN, which can exploit the knowledge from natural images without using any auxiliary observations. The LPN progressively reconstructs the high-spatial-resolution images in a coarse-to-fine fashion by using multiple pyramid levels. Second, spectral characteristics between the low- and high-resolution HSIs are studied by the non-negative dictionary learning (NDL), which is proposed to learn the common dictionary with non-negative constraints. The super-resolution results can finally be obtained by multiplying the learned dictionary and its corresponding sparse codes. Experimental results on three hyperspectral datasets demonstrate the feasibility of the proposed method in enhancing the spatial resolution of the HSI with preserving the spectral information simultaneously.https://www.mdpi.com/2072-4292/10/12/1939hyperspectral image (HSI)super-resolutiondeep Laplacian pyramid network (LPN)dictionary learning |
| spellingShingle | Zhi He Lin Liu Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network Remote Sensing hyperspectral image (HSI) super-resolution deep Laplacian pyramid network (LPN) dictionary learning |
| title | Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network |
| title_full | Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network |
| title_fullStr | Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network |
| title_full_unstemmed | Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network |
| title_short | Hyperspectral Image Super-Resolution Inspired by Deep Laplacian Pyramid Network |
| title_sort | hyperspectral image super resolution inspired by deep laplacian pyramid network |
| topic | hyperspectral image (HSI) super-resolution deep Laplacian pyramid network (LPN) dictionary learning |
| url | https://www.mdpi.com/2072-4292/10/12/1939 |
| work_keys_str_mv | AT zhihe hyperspectralimagesuperresolutioninspiredbydeeplaplacianpyramidnetwork AT linliu hyperspectralimagesuperresolutioninspiredbydeeplaplacianpyramidnetwork |