How Hyperspectral Image Unmixing and Denoising Can Boost Each Other
Hyperspectral linear unmixing and denoising are highly related hyperspectral image (HSI) analysis tasks. In particular, with the assumption of Gaussian noise, the linear model assumed for the HSI in the case of low-rank denoising is often the same as the one used in HSI unmixing. However, the optimi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/11/1728 |
| _version_ | 1797566833660788736 |
|---|---|
| author | Behnood Rasti Bikram Koirala Paul Scheunders Pedram Ghamisi |
| author_facet | Behnood Rasti Bikram Koirala Paul Scheunders Pedram Ghamisi |
| author_sort | Behnood Rasti |
| collection | DOAJ |
| description | Hyperspectral linear unmixing and denoising are highly related hyperspectral image (HSI) analysis tasks. In particular, with the assumption of Gaussian noise, the linear model assumed for the HSI in the case of low-rank denoising is often the same as the one used in HSI unmixing. However, the optimization criterion and the assumptions on the constraints are different. Additionally, noise reduction as a preprocessing step in hyperspectral data analysis is often ignored. The main goal of this paper is to study experimentally the influence of noise on the process of hyperspectral unmixing by: (1) investigating the effect of noise reduction as a preprocessing step on the performance of hyperspectral unmixing; (2) studying the relation between noise and different endmember selection strategies; (3) investigating the performance of HSI unmixing as an HSI denoiser; (4) comparing the denoising performance of spectral unmixing, state-of-the-art HSI denoising techniques, and the combination of both. All experiments are performed on simulated and real datasets. |
| first_indexed | 2024-03-10T19:33:00Z |
| format | Article |
| id | doaj.art-b9d68f023e954c7b84633dac600fd487 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T19:33:00Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b9d68f023e954c7b84633dac600fd4872023-11-20T02:01:41ZengMDPI AGRemote Sensing2072-42922020-05-011211172810.3390/rs12111728How Hyperspectral Image Unmixing and Denoising Can Boost Each OtherBehnood Rasti0Bikram Koirala1Paul Scheunders2Pedram Ghamisi3Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg for Resource Technology, Machine Learning Group, Chemnitzer Straße 40, 09599 Freiberg, GermanyImec-Visionlab, University of Antwerp (CDE) Universiteitsplein 1, B-2610 Antwerp, BelgiumImec-Visionlab, University of Antwerp (CDE) Universiteitsplein 1, B-2610 Antwerp, BelgiumHelmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg for Resource Technology, Machine Learning Group, Chemnitzer Straße 40, 09599 Freiberg, GermanyHyperspectral linear unmixing and denoising are highly related hyperspectral image (HSI) analysis tasks. In particular, with the assumption of Gaussian noise, the linear model assumed for the HSI in the case of low-rank denoising is often the same as the one used in HSI unmixing. However, the optimization criterion and the assumptions on the constraints are different. Additionally, noise reduction as a preprocessing step in hyperspectral data analysis is often ignored. The main goal of this paper is to study experimentally the influence of noise on the process of hyperspectral unmixing by: (1) investigating the effect of noise reduction as a preprocessing step on the performance of hyperspectral unmixing; (2) studying the relation between noise and different endmember selection strategies; (3) investigating the performance of HSI unmixing as an HSI denoiser; (4) comparing the denoising performance of spectral unmixing, state-of-the-art HSI denoising techniques, and the combination of both. All experiments are performed on simulated and real datasets.https://www.mdpi.com/2072-4292/12/11/1728hyperspectral imageunmixingdenoisinglinear mixing modellow-rank modelnoise reduction |
| spellingShingle | Behnood Rasti Bikram Koirala Paul Scheunders Pedram Ghamisi How Hyperspectral Image Unmixing and Denoising Can Boost Each Other Remote Sensing hyperspectral image unmixing denoising linear mixing model low-rank model noise reduction |
| title | How Hyperspectral Image Unmixing and Denoising Can Boost Each Other |
| title_full | How Hyperspectral Image Unmixing and Denoising Can Boost Each Other |
| title_fullStr | How Hyperspectral Image Unmixing and Denoising Can Boost Each Other |
| title_full_unstemmed | How Hyperspectral Image Unmixing and Denoising Can Boost Each Other |
| title_short | How Hyperspectral Image Unmixing and Denoising Can Boost Each Other |
| title_sort | how hyperspectral image unmixing and denoising can boost each other |
| topic | hyperspectral image unmixing denoising linear mixing model low-rank model noise reduction |
| url | https://www.mdpi.com/2072-4292/12/11/1728 |
| work_keys_str_mv | AT behnoodrasti howhyperspectralimageunmixinganddenoisingcanboosteachother AT bikramkoirala howhyperspectralimageunmixinganddenoisingcanboosteachother AT paulscheunders howhyperspectralimageunmixinganddenoisingcanboosteachother AT pedramghamisi howhyperspectralimageunmixinganddenoisingcanboosteachother |