Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images
Hyperspectral imaging technology has been popularly applied in remote sensing because it collects echoed signals from across the electromagnetic (EM) spectrum and thereby contributes fruitfully spatial-spectral information. However, the processing or storage of high-data-volume hyperspectral images...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9772246/ |
| _version_ | 1811255453068296192 |
|---|---|
| author | Yanming Zhang Ping Yuan Lijun Jiang Hong Tat Ewe |
| author_facet | Yanming Zhang Ping Yuan Lijun Jiang Hong Tat Ewe |
| author_sort | Yanming Zhang |
| collection | DOAJ |
| description | Hyperspectral imaging technology has been popularly applied in remote sensing because it collects echoed signals from across the electromagnetic (EM) spectrum and thereby contributes fruitfully spatial-spectral information. However, the processing or storage of high-data-volume hyperspectral images (HSIs), also viewed as snapshots varying with the EM spectrum, burdens the hardware resources, especially for the high spectral resolution and spatial resolution cases. To address this challenge, a novel unsupervised dimensionality reduction method based on the dynamic mode decomposition (DMD) algorithm is proposed to analyze hyperspectral data. This method decomposes the spatial-spectral HSIs in terms of spatial dynamic modes and corresponding spectral patterns. Then, these spatial-spectral patterns are combined to reconstruct the raw HSIs via a low-rank model. Furthermore, we extend the proposed DMD method to hyperspectral data in the tensor form and title it CubeDMD to actualize the compression of HSIs in horizontal, vertical, and spectral dimensions. Our proposed data-driven scheme is benchmarked by the real hyperspectral data measured at the Salinas scenes and Pavia University. It is demonstrated that the HSIs can be reconstructed accurately and effectively by the proposed low-rank model. The mean peak signal-to-noise ratio between the reconstructed and original HSIs can reach 31.47 dB, and the corresponding mean spectral angle mapper is only 0.1037. Our work provides a useful tool for the analysis of HSIs with a low-rank representation. |
| first_indexed | 2024-04-12T17:24:10Z |
| format | Article |
| id | doaj.art-1daa374a18a643f1bb6b8e95658669e5 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-12T17:24:10Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-1daa374a18a643f1bb6b8e95658669e52022-12-22T03:23:21ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01153877389010.1109/JSTARS.2022.31739999772246Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral ImagesYanming Zhang0https://orcid.org/0000-0002-6113-2168Ping Yuan1Lijun Jiang2Hong Tat Ewe3https://orcid.org/0000-0002-5195-1127Department of Electrical and Electronic Engineering, University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, Universiti Tunku Abdul Rahman (UTAR), Kuala Lumpur, MalaysiaHyperspectral imaging technology has been popularly applied in remote sensing because it collects echoed signals from across the electromagnetic (EM) spectrum and thereby contributes fruitfully spatial-spectral information. However, the processing or storage of high-data-volume hyperspectral images (HSIs), also viewed as snapshots varying with the EM spectrum, burdens the hardware resources, especially for the high spectral resolution and spatial resolution cases. To address this challenge, a novel unsupervised dimensionality reduction method based on the dynamic mode decomposition (DMD) algorithm is proposed to analyze hyperspectral data. This method decomposes the spatial-spectral HSIs in terms of spatial dynamic modes and corresponding spectral patterns. Then, these spatial-spectral patterns are combined to reconstruct the raw HSIs via a low-rank model. Furthermore, we extend the proposed DMD method to hyperspectral data in the tensor form and title it CubeDMD to actualize the compression of HSIs in horizontal, vertical, and spectral dimensions. Our proposed data-driven scheme is benchmarked by the real hyperspectral data measured at the Salinas scenes and Pavia University. It is demonstrated that the HSIs can be reconstructed accurately and effectively by the proposed low-rank model. The mean peak signal-to-noise ratio between the reconstructed and original HSIs can reach 31.47 dB, and the corresponding mean spectral angle mapper is only 0.1037. Our work provides a useful tool for the analysis of HSIs with a low-rank representation.https://ieeexplore.ieee.org/document/9772246/Cube dynamic mode decomposition (CubeDMD)hyperspectral images (HSIs)reconstructionthree-order tensorunsupervised dimensionality reduction |
| spellingShingle | Yanming Zhang Ping Yuan Lijun Jiang Hong Tat Ewe Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Cube dynamic mode decomposition (CubeDMD) hyperspectral images (HSIs) reconstruction three-order tensor unsupervised dimensionality reduction |
| title | Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images |
| title_full | Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images |
| title_fullStr | Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images |
| title_full_unstemmed | Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images |
| title_short | Novel Data-Driven Spatial-Spectral Correlated Scheme for Dimensionality Reduction of Hyperspectral Images |
| title_sort | novel data driven spatial spectral correlated scheme for dimensionality reduction of hyperspectral images |
| topic | Cube dynamic mode decomposition (CubeDMD) hyperspectral images (HSIs) reconstruction three-order tensor unsupervised dimensionality reduction |
| url | https://ieeexplore.ieee.org/document/9772246/ |
| work_keys_str_mv | AT yanmingzhang noveldatadrivenspatialspectralcorrelatedschemefordimensionalityreductionofhyperspectralimages AT pingyuan noveldatadrivenspatialspectralcorrelatedschemefordimensionalityreductionofhyperspectralimages AT lijunjiang noveldatadrivenspatialspectralcorrelatedschemefordimensionalityreductionofhyperspectralimages AT hongtatewe noveldatadrivenspatialspectralcorrelatedschemefordimensionalityreductionofhyperspectralimages |