A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization
Hyperspectral (HS) images can provide abundant and fine spectral information on land surface. However, their applications may be limited by their narrow bandwidth and small coverage area. In this paper, we propose an HS image simulation method based on nonnegative matrix factorization (NMF), which a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/20/2416 |
| _version_ | 1818975383038459904 |
|---|---|
| author | Zehua Huang Qi Chen Qihao Chen Xiuguo Liu Hao He |
| author_facet | Zehua Huang Qi Chen Qihao Chen Xiuguo Liu Hao He |
| author_sort | Zehua Huang |
| collection | DOAJ |
| description | Hyperspectral (HS) images can provide abundant and fine spectral information on land surface. However, their applications may be limited by their narrow bandwidth and small coverage area. In this paper, we propose an HS image simulation method based on nonnegative matrix factorization (NMF), which aims at generating HS images using existing multispectral (MS) data. Our main novelty is proposing a spectral transformation matrix and new simulation method. First, we develop a spectral transformation matrix that transforms HS endmembers into MS endmembers. Second, we utilize an iteration scheme to optimize the HS and MS endmembers. The test MS image is then factorized by the MS endmembers to obtain the abundance matrix. The result image is constructed by multiplying the abundance matrix by the HS endmembers. Experiments prove that our method provides high spectral quality by combining prior spectral endmembers. The iteration schemes reduce the simulation error and improve the accuracy of the results. In comparative trials, the spectral angle, RMSE, and correlation coefficient of our method are 5.986, 284.6, and 0.905, respectively. Thus, our method outperforms other simulation methods. |
| first_indexed | 2024-12-20T15:55:04Z |
| format | Article |
| id | doaj.art-74442dcc0f9b46c4ad668a0bd768a3d9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T15:55:04Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-74442dcc0f9b46c4ad668a0bd768a3d92022-12-21T19:34:30ZengMDPI AGRemote Sensing2072-42922019-10-011120241610.3390/rs11202416rs11202416A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix FactorizationZehua Huang0Qi Chen1Qihao Chen2Xiuguo Liu3Hao He4School of Geography and Information Engineering, China University of Geoscience (Wuhan), Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geoscience (Wuhan), Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geoscience (Wuhan), Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geoscience (Wuhan), Wuhan 430074, ChinaFaculty of Civil Engineering, Xinjiang University, Wulumuqi 830047, ChinaHyperspectral (HS) images can provide abundant and fine spectral information on land surface. However, their applications may be limited by their narrow bandwidth and small coverage area. In this paper, we propose an HS image simulation method based on nonnegative matrix factorization (NMF), which aims at generating HS images using existing multispectral (MS) data. Our main novelty is proposing a spectral transformation matrix and new simulation method. First, we develop a spectral transformation matrix that transforms HS endmembers into MS endmembers. Second, we utilize an iteration scheme to optimize the HS and MS endmembers. The test MS image is then factorized by the MS endmembers to obtain the abundance matrix. The result image is constructed by multiplying the abundance matrix by the HS endmembers. Experiments prove that our method provides high spectral quality by combining prior spectral endmembers. The iteration schemes reduce the simulation error and improve the accuracy of the results. In comparative trials, the spectral angle, RMSE, and correlation coefficient of our method are 5.986, 284.6, and 0.905, respectively. Thus, our method outperforms other simulation methods.https://www.mdpi.com/2072-4292/11/20/2416hyperspectral imagehyperspectral image simulationpseudo-hyperspectral imagerynonnegative matrix factorizationspectral reconstruction |
| spellingShingle | Zehua Huang Qi Chen Qihao Chen Xiuguo Liu Hao He A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization Remote Sensing hyperspectral image hyperspectral image simulation pseudo-hyperspectral imagery nonnegative matrix factorization spectral reconstruction |
| title | A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization |
| title_full | A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization |
| title_fullStr | A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization |
| title_full_unstemmed | A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization |
| title_short | A Novel Hyperspectral Image Simulation Method Based on Nonnegative Matrix Factorization |
| title_sort | novel hyperspectral image simulation method based on nonnegative matrix factorization |
| topic | hyperspectral image hyperspectral image simulation pseudo-hyperspectral imagery nonnegative matrix factorization spectral reconstruction |
| url | https://www.mdpi.com/2072-4292/11/20/2416 |
| work_keys_str_mv | AT zehuahuang anovelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT qichen anovelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT qihaochen anovelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT xiuguoliu anovelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT haohe anovelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT zehuahuang novelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT qichen novelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT qihaochen novelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT xiuguoliu novelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization AT haohe novelhyperspectralimagesimulationmethodbasedonnonnegativematrixfactorization |