Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence

Hyperspectral unmixing (HU) has become an important technique in exploiting hyperspectral data since it decomposes a mixed pixel into a collection of endmembers weighted by fractional abundances. The endmembers of a hyperspectral image (HSI) are more likely to be generated by independent sources and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	E. M. M. B. Ekanayake, H. M. H. K. Weerasooriya, D. Y. L. Ranasinghe, S. Herath, B. Rathnayake, G. M. R. I. Godaliyadda, M. P. B. Ekanayake, H. M. V. R. Herath
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Blind source separation constrained endmember independence Gaussianity hyperspectral unmixing (HU) kurtosis Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/9da50be38a264431ad6d9883076df7be
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9da50be38a264431ad6d9883076df7be
record_format	dspace
spelling	oai:doaj.org-article:9da50be38a264431ad6d9883076df7be2021-12-03T00:00:14ZConstrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence2151-153510.1109/JSTARS.2021.3126664https://doaj.org/article/9da50be38a264431ad6d9883076df7be2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9609564/https://doaj.org/toc/2151-1535Hyperspectral unmixing (HU) has become an important technique in exploiting hyperspectral data since it decomposes a mixed pixel into a collection of endmembers weighted by fractional abundances. The endmembers of a hyperspectral image (HSI) are more likely to be generated by independent sources and be mixed in a macroscopic degree before arriving at the sensor element of the imaging spectrometer as mixed spectra. Over the past few decades, many attempts have focused on imposing auxiliary regularizes on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum regularizer to extract endmembers, this article presents a novel blind HU algorithm, referred to as kurtosis-based smooth nonnegative matrix factorization (KbSNMF) which incorporates a novel regularizer based on the statistical independence of the probability density functions of endmember spectra. Imposing this regularizer on the conventional NMF framework promotes the extraction of independent endmembers while further enhancing the parts-based representation of data. Experiments conducted on diverse synthetic HSI datasets (with numerous numbers of endmembers, spectral bands, pixels, and noise levels) and three standard real HSI datasets demonstrate the validity of the proposed KbSNMF algorithm compared to several state-of-the-art NMF-based HU baselines. The proposed algorithm exhibits superior performance especially in terms of extracting endmember spectra from hyperspectral data; therefore, it could uplift the performance of recent deep learning HU methods which utilize the endmember spectra as supervisory input data for abundance extraction.E. M. M. B. EkanayakeH. M. H. K. WeerasooriyaD. Y. L. RanasingheS. HerathB. RathnayakeG. M. R. I. GodaliyaddaM. P. B. EkanayakeH. M. V. R. HerathIEEEarticleBlind source separationconstrainedendmember independenceGaussianityhyperspectral unmixing (HU)kurtosisOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11853-11869 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Blind source separation constrained endmember independence Gaussianity hyperspectral unmixing (HU) kurtosis Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Blind source separation constrained endmember independence Gaussianity hyperspectral unmixing (HU) kurtosis Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 E. M. M. B. Ekanayake H. M. H. K. Weerasooriya D. Y. L. Ranasinghe S. Herath B. Rathnayake G. M. R. I. Godaliyadda M. P. B. Ekanayake H. M. V. R. Herath Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence
description	Hyperspectral unmixing (HU) has become an important technique in exploiting hyperspectral data since it decomposes a mixed pixel into a collection of endmembers weighted by fractional abundances. The endmembers of a hyperspectral image (HSI) are more likely to be generated by independent sources and be mixed in a macroscopic degree before arriving at the sensor element of the imaging spectrometer as mixed spectra. Over the past few decades, many attempts have focused on imposing auxiliary regularizes on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum regularizer to extract endmembers, this article presents a novel blind HU algorithm, referred to as kurtosis-based smooth nonnegative matrix factorization (KbSNMF) which incorporates a novel regularizer based on the statistical independence of the probability density functions of endmember spectra. Imposing this regularizer on the conventional NMF framework promotes the extraction of independent endmembers while further enhancing the parts-based representation of data. Experiments conducted on diverse synthetic HSI datasets (with numerous numbers of endmembers, spectral bands, pixels, and noise levels) and three standard real HSI datasets demonstrate the validity of the proposed KbSNMF algorithm compared to several state-of-the-art NMF-based HU baselines. The proposed algorithm exhibits superior performance especially in terms of extracting endmember spectra from hyperspectral data; therefore, it could uplift the performance of recent deep learning HU methods which utilize the endmember spectra as supervisory input data for abundance extraction.
format	article
author	E. M. M. B. Ekanayake H. M. H. K. Weerasooriya D. Y. L. Ranasinghe S. Herath B. Rathnayake G. M. R. I. Godaliyadda M. P. B. Ekanayake H. M. V. R. Herath
author_facet	E. M. M. B. Ekanayake H. M. H. K. Weerasooriya D. Y. L. Ranasinghe S. Herath B. Rathnayake G. M. R. I. Godaliyadda M. P. B. Ekanayake H. M. V. R. Herath
author_sort	E. M. M. B. Ekanayake
title	Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence
title_short	Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence
title_full	Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence
title_fullStr	Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence
title_full_unstemmed	Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence
title_sort	constrained nonnegative matrix factorization for blind hyperspectral unmixing incorporating endmember independence
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/9da50be38a264431ad6d9883076df7be
work_keys_str_mv	AT emmbekanayake constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT hmhkweerasooriya constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT dylranasinghe constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT sherath constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT brathnayake constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT gmrigodaliyadda constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT mpbekanayake constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence AT hmvrherath constrainednonnegativematrixfactorizationforblindhyperspectralunmixingincorporatingendmemberindependence
_version_	1718374003925581824

Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence

Ejemplares similares