Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability
Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/10/11/1706 |
id |
doaj-aa9fb83fc0294b4e83ee62a9b7c2d8ad |
---|---|
record_format |
Article |
spelling |
doaj-aa9fb83fc0294b4e83ee62a9b7c2d8ad2020-11-25T02:42:25ZengMDPI AGRemote Sensing2072-42922018-10-011011170610.3390/rs10111706rs10111706Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class VariabilityCharlotte Revel0Yannick Deville1Véronique Achard2Xavier Briottet3Christiane Weber4IRAP (Institut de Recherche en Astrophysique et Planétologie), Université de Toulouse, UPS, CNRS, CNES, 14 avenue Edouard Belin, F-31400 Toulouse, FranceIRAP (Institut de Recherche en Astrophysique et Planétologie), Université de Toulouse, UPS, CNRS, CNES, 14 avenue Edouard Belin, F-31400 Toulouse, FranceONERA The French Aerospace Lab, Department of Theoretical and Applied Optics, F-31400 Toulouse, FranceONERA The French Aerospace Lab, Department of Theoretical and Applied Optics, F-31400 Toulouse, FranceUMR TETIS, Maison de la Télédétection, 34000 Montpellier, FranceBlind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no longer valid in the presence of intra-class variability due to illumination conditions, weathering, slight variations of the pure materials, etc. In this paper, we first describe the results of investigations highlighting intra-class variability measured in real images. Considering these results, a new formulation of the linear mixing model is presented leading to two new methods. Unconstrained pixel-by-pixel NMF (UP-NMF) is a new blind source separation method based on the assumption of a linear mixing model, which can deal with intra-class variability. To overcome the limitations of UP-NMF, an extended method is also proposed, named Inertia-constrained Pixel-by-pixel NMF (IP-NMF). For each sensed spectrum, these extended versions of NMF extract a corresponding set of source spectra. A constraint is set to limit the spreading of each source’s estimates in IP-NMF. The proposed methods are first tested on a semi-synthetic data set built with spectra extracted from a real hyperspectral image and then numerically mixed. We thus demonstrate the interest of our methods for realistic source variabilities. Finally, IP-NMF is tested on a real data set and it is shown to yield better performance than state of the art methods.https://www.mdpi.com/2072-4292/10/11/1706nonnegative matrix factorisation (NMF)blind source separationhyperspectral unmixingintra-class variability |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Charlotte Revel Yannick Deville Véronique Achard Xavier Briottet Christiane Weber |
spellingShingle |
Charlotte Revel Yannick Deville Véronique Achard Xavier Briottet Christiane Weber Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability Remote Sensing nonnegative matrix factorisation (NMF) blind source separation hyperspectral unmixing intra-class variability |
author_facet |
Charlotte Revel Yannick Deville Véronique Achard Xavier Briottet Christiane Weber |
author_sort |
Charlotte Revel |
title |
Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability |
title_short |
Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability |
title_full |
Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability |
title_fullStr |
Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability |
title_full_unstemmed |
Inertia-Constrained Pixel-by-Pixel Nonnegative Matrix Factorisation: A Hyperspectral Unmixing Method Dealing with Intra-Class Variability |
title_sort |
inertia-constrained pixel-by-pixel nonnegative matrix factorisation: a hyperspectral unmixing method dealing with intra-class variability |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2018-10-01 |
description |
Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no longer valid in the presence of intra-class variability due to illumination conditions, weathering, slight variations of the pure materials, etc. In this paper, we first describe the results of investigations highlighting intra-class variability measured in real images. Considering these results, a new formulation of the linear mixing model is presented leading to two new methods. Unconstrained pixel-by-pixel NMF (UP-NMF) is a new blind source separation method based on the assumption of a linear mixing model, which can deal with intra-class variability. To overcome the limitations of UP-NMF, an extended method is also proposed, named Inertia-constrained Pixel-by-pixel NMF (IP-NMF). For each sensed spectrum, these extended versions of NMF extract a corresponding set of source spectra. A constraint is set to limit the spreading of each source’s estimates in IP-NMF. The proposed methods are first tested on a semi-synthetic data set built with spectra extracted from a real hyperspectral image and then numerically mixed. We thus demonstrate the interest of our methods for realistic source variabilities. Finally, IP-NMF is tested on a real data set and it is shown to yield better performance than state of the art methods. |
topic |
nonnegative matrix factorisation (NMF) blind source separation hyperspectral unmixing intra-class variability |
url |
https://www.mdpi.com/2072-4292/10/11/1706 |
work_keys_str_mv |
AT charlotterevel inertiaconstrainedpixelbypixelnonnegativematrixfactorisationahyperspectralunmixingmethoddealingwithintraclassvariability AT yannickdeville inertiaconstrainedpixelbypixelnonnegativematrixfactorisationahyperspectralunmixingmethoddealingwithintraclassvariability AT veroniqueachard inertiaconstrainedpixelbypixelnonnegativematrixfactorisationahyperspectralunmixingmethoddealingwithintraclassvariability AT xavierbriottet inertiaconstrainedpixelbypixelnonnegativematrixfactorisationahyperspectralunmixingmethoddealingwithintraclassvariability AT christianeweber inertiaconstrainedpixelbypixelnonnegativematrixfactorisationahyperspectralunmixingmethoddealingwithintraclassvariability |
_version_ |
1724774182898630656 |