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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-08
Hauptverfasser: E M M B Ekanayake, H M H K Weerasooriya, Ranasinghe, D Y L, Herath, S, Rathnayake, B, G M R I Godaliyadda, Ekanayake, M P B, H M V R Herath
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator E M M B Ekanayake
H M H K Weerasooriya
Ranasinghe, D Y L
Herath, S
Rathnayake, B
G M R I Godaliyadda
Ekanayake, M P B
H M V R Herath
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 constraints on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum constraint to extract endmembers, this paper presents a novel blind HU algorithm, referred to as Kurtosis-based Smooth Nonnegative Matrix Factorization (KbSNMF) which incorporates a novel constraint based on the statistical independence of the probability density functions of endmember spectra. Imposing this constraint 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
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2370236831</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2370236831</sourcerecordid><originalsourceid>FETCH-proquest_journals_23702368313</originalsourceid><addsrcrecordid>eNqNi8EOAUEQRCcSCWH_oRNnyZphORPCgRNnGbttM7LbPXqG4OvNwQe4VKWqXnVUXxszGS-mWvdUFsItz3NdzPVsZvpKVkwhinWEFRyYCGsb3RNhb6O4F2xsGVncJ5VMcGWBZeOogu3bowSPZfo2cKLWvRzV4Khk8SwJT2lNVYvtBQV2VKHHJFTiUHWvtgmY_XygRpv1cbUde-H7A0M83_ghlKazNvNcm2JhJuY_6gtW2Ez8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2370236831</pqid></control><display><type>article</type><title>Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence</title><source>Free E- Journals</source><creator>E M M B Ekanayake ; H M H K Weerasooriya ; Ranasinghe, D Y L ; Herath, S ; Rathnayake, B ; G M R I Godaliyadda ; Ekanayake, M P B ; H M V R Herath</creator><creatorcontrib>E M M B Ekanayake ; H M H K Weerasooriya ; Ranasinghe, D Y L ; Herath, S ; Rathnayake, B ; G M R I Godaliyadda ; Ekanayake, M P B ; H M V R Herath</creatorcontrib><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 constraints on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum constraint to extract endmembers, this paper presents a novel blind HU algorithm, referred to as Kurtosis-based Smooth Nonnegative Matrix Factorization (KbSNMF) which incorporates a novel constraint based on the statistical independence of the probability density functions of endmember spectra. Imposing this constraint 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.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Constraints ; Factorization ; Hyperspectral imaging ; Imaging spectrometers ; Kurtosis ; Machine learning ; Probability density functions ; Remote sensing ; Signal processing ; Spatial resolution ; Spectra ; Spectral bands ; Spectrometers ; Statistical analysis ; Uplift</subject><ispartof>arXiv.org, 2021-08</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>E M M B Ekanayake</creatorcontrib><creatorcontrib>H M H K Weerasooriya</creatorcontrib><creatorcontrib>Ranasinghe, D Y L</creatorcontrib><creatorcontrib>Herath, S</creatorcontrib><creatorcontrib>Rathnayake, B</creatorcontrib><creatorcontrib>G M R I Godaliyadda</creatorcontrib><creatorcontrib>Ekanayake, M P B</creatorcontrib><creatorcontrib>H M V R Herath</creatorcontrib><title>Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence</title><title>arXiv.org</title><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 constraints on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum constraint to extract endmembers, this paper presents a novel blind HU algorithm, referred to as Kurtosis-based Smooth Nonnegative Matrix Factorization (KbSNMF) which incorporates a novel constraint based on the statistical independence of the probability density functions of endmember spectra. Imposing this constraint 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.</description><subject>Algorithms</subject><subject>Constraints</subject><subject>Factorization</subject><subject>Hyperspectral imaging</subject><subject>Imaging spectrometers</subject><subject>Kurtosis</subject><subject>Machine learning</subject><subject>Probability density functions</subject><subject>Remote sensing</subject><subject>Signal processing</subject><subject>Spatial resolution</subject><subject>Spectra</subject><subject>Spectral bands</subject><subject>Spectrometers</subject><subject>Statistical analysis</subject><subject>Uplift</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi8EOAUEQRCcSCWH_oRNnyZphORPCgRNnGbttM7LbPXqG4OvNwQe4VKWqXnVUXxszGS-mWvdUFsItz3NdzPVsZvpKVkwhinWEFRyYCGsb3RNhb6O4F2xsGVncJ5VMcGWBZeOogu3bowSPZfo2cKLWvRzV4Khk8SwJT2lNVYvtBQV2VKHHJFTiUHWvtgmY_XygRpv1cbUde-H7A0M83_ghlKazNvNcm2JhJuY_6gtW2Ez8</recordid><startdate>20210807</startdate><enddate>20210807</enddate><creator>E M M B Ekanayake</creator><creator>H M H K Weerasooriya</creator><creator>Ranasinghe, D Y L</creator><creator>Herath, S</creator><creator>Rathnayake, B</creator><creator>G M R I Godaliyadda</creator><creator>Ekanayake, M P B</creator><creator>H M V R Herath</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210807</creationdate><title>Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence</title><author>E M M B Ekanayake ; H M H K Weerasooriya ; Ranasinghe, D Y L ; Herath, S ; Rathnayake, B ; G M R I Godaliyadda ; Ekanayake, M P B ; H M V R Herath</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23702368313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Constraints</topic><topic>Factorization</topic><topic>Hyperspectral imaging</topic><topic>Imaging spectrometers</topic><topic>Kurtosis</topic><topic>Machine learning</topic><topic>Probability density functions</topic><topic>Remote sensing</topic><topic>Signal processing</topic><topic>Spatial resolution</topic><topic>Spectra</topic><topic>Spectral bands</topic><topic>Spectrometers</topic><topic>Statistical analysis</topic><topic>Uplift</topic><toplevel>online_resources</toplevel><creatorcontrib>E M M B Ekanayake</creatorcontrib><creatorcontrib>H M H K Weerasooriya</creatorcontrib><creatorcontrib>Ranasinghe, D Y L</creatorcontrib><creatorcontrib>Herath, S</creatorcontrib><creatorcontrib>Rathnayake, B</creatorcontrib><creatorcontrib>G M R I Godaliyadda</creatorcontrib><creatorcontrib>Ekanayake, M P B</creatorcontrib><creatorcontrib>H M V R Herath</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>E M M B Ekanayake</au><au>H M H K Weerasooriya</au><au>Ranasinghe, D Y L</au><au>Herath, S</au><au>Rathnayake, B</au><au>G M R I Godaliyadda</au><au>Ekanayake, M P B</au><au>H M V R Herath</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence</atitle><jtitle>arXiv.org</jtitle><date>2021-08-07</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>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 constraints on the conventional nonnegative matrix factorization (NMF) framework in order to effectively unmix these mixed spectra. As a promising step toward finding an optimum constraint to extract endmembers, this paper presents a novel blind HU algorithm, referred to as Kurtosis-based Smooth Nonnegative Matrix Factorization (KbSNMF) which incorporates a novel constraint based on the statistical independence of the probability density functions of endmember spectra. Imposing this constraint 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.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2370236831
source Free E- Journals
subjects Algorithms
Constraints
Factorization
Hyperspectral imaging
Imaging spectrometers
Kurtosis
Machine learning
Probability density functions
Remote sensing
Signal processing
Spatial resolution
Spectra
Spectral bands
Spectrometers
Statistical analysis
Uplift
title Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T00%3A04%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Constrained%20Nonnegative%20Matrix%20Factorization%20for%20Blind%20Hyperspectral%20Unmixing%20incorporating%20Endmember%20Independence&rft.jtitle=arXiv.org&rft.au=E%20M%20M%20B%20Ekanayake&rft.date=2021-08-07&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2370236831%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2370236831&rft_id=info:pmid/&rfr_iscdi=true