LSTM-DNN Based Autoencoder Network for Nonlinear Hyperspectral Image Unmixing

Blind hyperspectral unmixing is an important technique in hyperspectral image analysis, aiming at estimating endmembers and their respective fractional abundances. Consider the limitations of using the linear model, nonlinear unmixing methods have been studied under different model assumptions. Howe...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE journal of selected topics in signal processing Ročník 15; číslo 2; s. 295 - 309
Hlavní autoři:	Zhao, Min, Yan, Longbin, Chen, Jie
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.02.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Artificial neural networks attention recurrent neural network autoencoder network Correlation Decoding Hyperspectral imaging Hyperspectral unmixing Image analysis Mathematical model Neural networks nonlinear unmixing Regularization Spectral correlation Task analysis Three-dimensional displays
ISSN:	1932-4553, 1941-0484
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Blind hyperspectral unmixing is an important technique in hyperspectral image analysis, aiming at estimating endmembers and their respective fractional abundances. Consider the limitations of using the linear model, nonlinear unmixing methods have been studied under different model assumptions. However, existing nonlinear unmixing algorithms do not fully exploit spectral and spatial correlation information. This paper proposes a nonsymmetric autoencoder network to overcome this issue. The proposed scheme benefits from the universal modeling ability of deep neural networks and enables to learn the nonlinear relation from the data. Particularly, the long short-term memory network (LSTM) structure is included to capture spectral correlation information, and a spatial regularization is introduced to improve the spatial continuity of results. An attention mechanism is also used to further enhance the unmixing performance. Experiments with synthetic and real data are conducted to illustrate the effectiveness of the proposed method.
AbstractList	Blind hyperspectral unmixing is an important technique in hyperspectral image analysis, aiming at estimating endmembers and their respective fractional abundances. Consider the limitations of using the linear model, nonlinear unmixing methods have been studied under different model assumptions. However, existing nonlinear unmixing algorithms do not fully exploit spectral and spatial correlation information. This paper proposes a nonsymmetric autoencoder network to overcome this issue. The proposed scheme benefits from the universal modeling ability of deep neural networks and enables to learn the nonlinear relation from the data. Particularly, the long short-term memory network (LSTM) structure is included to capture spectral correlation information, and a spatial regularization is introduced to improve the spatial continuity of results. An attention mechanism is also used to further enhance the unmixing performance. Experiments with synthetic and real data are conducted to illustrate the effectiveness of the proposed method.
Author	Zhao, Min Chen, Jie Yan, Longbin
Author_xml	– sequence: 1 givenname: Min orcidid: 0000-0003-3258-8358 surname: Zhao fullname: Zhao, Min email: minzhao@mail.nwpu.edu.cn organization: School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China – sequence: 2 givenname: Longbin surname: Yan fullname: Yan, Longbin email: yanlongbin@mail.nwpu.edu.cn organization: School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China – sequence: 3 givenname: Jie orcidid: 0000-0003-2306-8860 surname: Chen fullname: Chen, Jie email: dr.jie.chen@ieee.org organization: School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China
BookMark	eNp9kM9PwjAUxxuDiYD-A3pZ4nnYru3WHRF_gAE0Ac5Lu72R4mhnO6L89w4hHjx4et_D9_Pey6eHOsYaQOia4AEhOL17WSwXb4MIR2RAMY9oTM5Ql6SMhJgJ1jlkGoWMc3qBet5vMOZJTFgXzaaL5Sx8mM-De-mhCIa7xoLJbQEumEPzad17UNo2W1NpA9IF430NzteQN05WwWQr1xCszFZ_abO-ROelrDxcnWYfrZ4el6NxOH19noyG0zCPUt6EQKKEpYwqQVJeEExKweKcSaEKmlJJC56o9jsqRU6FSBXhwBIaF0oqlXDFaB_dHvfWzn7swDfZxu6caU9mEUtpjBnDSdsSx1burPcOyizXjWy0Ne3rusoIzg7ysh952UFedpLXotEftHZ6K93-f-jmCGkA-AVa8TFNEvoNs757lw
CODEN	IJSTGY
CitedBy_id	crossref_primary_10_3390_rs17172968 crossref_primary_10_1109_JSTARS_2021_3126755 crossref_primary_10_1016_j_asr_2022_06_028 crossref_primary_10_1109_JSTARS_2022_3188565 crossref_primary_10_1007_s10772_022_09962_z crossref_primary_10_1109_TGRS_2024_3422495 crossref_primary_10_1109_JSTARS_2022_3168333 crossref_primary_10_1109_JSTARS_2025_3584232 crossref_primary_10_1109_TCI_2023_3321985 crossref_primary_10_3390_rs15245694 crossref_primary_10_1016_j_compag_2023_108382 crossref_primary_10_1109_JSTARS_2021_3132283 crossref_primary_10_1109_TGRS_2022_3202490 crossref_primary_10_1109_ACCESS_2021_3099631 crossref_primary_10_1109_TGRS_2023_3324018 crossref_primary_10_1109_TMC_2024_3475634 crossref_primary_10_1109_JSTARS_2024_3387750 crossref_primary_10_1109_TGRS_2024_3360714 crossref_primary_10_1109_TGRS_2024_3363427 crossref_primary_10_1109_TGRS_2025_3551119 crossref_primary_10_1109_JSTARS_2021_3126664 crossref_primary_10_1109_TCI_2024_3369410 crossref_primary_10_1109_TGRS_2024_3393570 crossref_primary_10_1109_JSTARS_2022_3175257 crossref_primary_10_1109_TGRS_2025_3540378 crossref_primary_10_1109_JSEN_2022_3143852 crossref_primary_10_1109_TIP_2024_3374093 crossref_primary_10_3390_rs14163947 crossref_primary_10_1016_j_inffus_2025_103712 crossref_primary_10_1109_JSTARS_2024_3359647 crossref_primary_10_1109_TGRS_2023_3304484 crossref_primary_10_1080_22797254_2023_2277213 crossref_primary_10_1109_TGRS_2022_3168712 crossref_primary_10_1109_JSTARS_2021_3140154 crossref_primary_10_1109_JSTSP_2022_3179806 crossref_primary_10_1016_j_eswa_2023_119904 crossref_primary_10_1109_TGRS_2023_3321839 crossref_primary_10_3788_IRLA20250131 crossref_primary_10_1109_JSEN_2024_3373477 crossref_primary_10_1109_JSTARS_2025_3593668 crossref_primary_10_1109_TGRS_2024_3377472 crossref_primary_10_3390_rs15102619 crossref_primary_10_1177_00202940221109778 crossref_primary_10_32604_cmc_2022_027936 crossref_primary_10_1109_JSTARS_2025_3593442
Cites_doi	10.1109/TIP.2015.2468177 10.1109/ICASSP.2013.6638947 10.1109/JSTSP.2010.2088377 10.1080/01431160802558659 10.1109/79.974727 10.1109/TGRS.2015.2453915 10.1109/JSTARS.2012.2194696 10.1109/JSTARS.2014.2320576 10.1109/TIP.2012.2187668 10.1162/neco.1997.9.8.1735 10.3390/rs11050529 10.1109/LGRS.2018.2841400 10.1109/IGARSS.2017.8127062 10.3115/v1/D14-1179 10.1109/TGRS.2018.2868690 10.1016/j.neucom.2018.02.105 10.1109/JSTARS.2017.2655112 10.1109/IGARSS.2019.8900297 10.1109/TSP.2012.2222390 10.1109/TGRS.2018.2856929 10.1109/LGRS.2012.2189934 10.1016/0034-4257(94)90107-4 10.18653/v1/D16-1244 10.1109/LGRS.2018.2857804 10.1109/JSTARS.2019.2905099 10.1109/IGARSS.2011.6049492 10.1016/j.rse.2007.07.028 10.1109/TGRS.2005.844293 10.1109/36.911111 10.1109/ACCESS.2018.2818280 10.1109/JSTARS.2020.2966512 10.1109/TIP.2016.2627815 10.1109/TIP.2014.2314022 10.1109/TGRS.2008.918089 10.1109/TGRS.2018.2827407 10.1109/MSP.2013.2279731 10.1179/174313110X12771950995716 10.1126/science.260.5107.509 10.1109/TGRS.2018.2890633 10.1109/TGRS.2011.2160950 10.1109/TGRS.2018.2849692 10.1109/LGRS.2019.2900733 10.1109/TGRS.2016.2636241
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD H8D L7M
DOI	10.1109/JSTSP.2021.3052361
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Aerospace Database Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0484
EndPage	309
ExternalDocumentID	10_1109_JSTSP_2021_3052361 9326377
Genre	orig-research
GrantInformation_xml	– fundername: Northwestern Polytechnical University funderid: 10.13039/501100002663 – fundername: Higher Education Discipline Innovation Project; 111 Project grantid: B18041 funderid: 10.13039/501100013314 – fundername: National Key Research and Development Program of China grantid: 2018AAA0102200
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL RIA RIE RNS AAYXX CITATION 7SP 8FD H8D L7M
ID	FETCH-LOGICAL-c295t-e1274943b8195d101f846c4a8bd393a3d57b6143a8c3889b15e4736dbabb75b43
IEDL.DBID	RIE
ISICitedReferencesCount	51
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000622098600012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1932-4553
IngestDate	Mon Jun 30 10:17:44 EDT 2025 Sat Nov 29 04:10:33 EST 2025 Tue Nov 18 20:45:57 EST 2025 Wed Aug 27 02:30:24 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c295t-e1274943b8195d101f846c4a8bd393a3d57b6143a8c3889b15e4736dbabb75b43
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2306-8860 0000-0003-3258-8358
PQID	2493604407
PQPubID	75721
PageCount	15
ParticipantIDs	crossref_citationtrail_10_1109_JSTSP_2021_3052361 proquest_journals_2493604407 crossref_primary_10_1109_JSTSP_2021_3052361 ieee_primary_9326377
PublicationCentury	2000
PublicationDate	2021-02-01
PublicationDateYYYYMMDD	2021-02-01
PublicationDate_xml	– month: 02 year: 2021 text: 2021-02-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE journal of selected topics in signal processing
PublicationTitleAbbrev	JSTSP
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref34 ref12 ref37 ref15 ref36 ref14 ref31 ref30 ref33 ref11 ref32 ref10 ref2 ref1 ref17 ref38 ref16 ref19 ref18 luo (ref35) 2013; 10 bahdanau (ref41) 2014 borsoi (ref26) 2019; 6 ref46 ref24 ref45 ref23 graves (ref39) 2013 ref47 ref25 ref20 ref42 ref22 ref44 ref21 ref43 ref28 ref27 mnih (ref40) 0 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref46 doi: 10.1109/TIP.2015.2468177 – ident: ref31 doi: 10.1109/ICASSP.2013.6638947 – ident: ref44 doi: 10.1109/JSTSP.2010.2088377 – ident: ref9 doi: 10.1080/01431160802558659 – year: 2014 ident: ref41 article-title: Neural machine translation by jointly learning to align and translate – ident: ref5 doi: 10.1109/79.974727 – ident: ref37 doi: 10.1109/TGRS.2015.2453915 – ident: ref1 doi: 10.1109/JSTARS.2012.2194696 – ident: ref7 doi: 10.1109/JSTARS.2014.2320576 – ident: ref11 doi: 10.1109/TIP.2012.2187668 – ident: ref38 doi: 10.1162/neco.1997.9.8.1735 – ident: ref14 doi: 10.3390/rs11050529 – ident: ref25 doi: 10.1109/LGRS.2018.2841400 – ident: ref23 doi: 10.1109/IGARSS.2017.8127062 – ident: ref30 doi: 10.3115/v1/D14-1179 – ident: ref21 doi: 10.1109/TGRS.2018.2868690 – ident: ref32 doi: 10.1016/j.neucom.2018.02.105 – ident: ref17 doi: 10.1109/JSTARS.2017.2655112 – year: 2013 ident: ref39 article-title: Generating sequences with recurrent neural networks – ident: ref27 doi: 10.1109/IGARSS.2019.8900297 – ident: ref13 doi: 10.1109/TSP.2012.2222390 – ident: ref24 doi: 10.1109/TGRS.2018.2856929 – volume: 10 start-page: 24 year: 2013 ident: ref35 article-title: Empirical automatic estimation of the number of endmembers in hyperspectral images publication-title: IEEE Geosci Remote Sens Lett doi: 10.1109/LGRS.2012.2189934 – start-page: 2204 year: 0 ident: ref40 article-title: Recurrent models of visual attention publication-title: Proc Adv Neural Inf Process Syst – ident: ref8 doi: 10.1016/0034-4257(94)90107-4 – ident: ref42 doi: 10.18653/v1/D16-1244 – ident: ref19 doi: 10.1109/LGRS.2018.2857804 – ident: ref47 doi: 10.1109/JSTARS.2019.2905099 – ident: ref10 doi: 10.1109/IGARSS.2011.6049492 – volume: 6 start-page: 374 year: 2019 ident: ref26 article-title: Deep generative endmember modeling: An application to unsupervised spectral unmixing publication-title: I IEEE Transactions on Computers – ident: ref2 doi: 10.1016/j.rse.2007.07.028 – ident: ref43 doi: 10.1109/TGRS.2005.844293 – ident: ref6 doi: 10.1109/36.911111 – ident: ref22 doi: 10.1109/ACCESS.2018.2818280 – ident: ref28 doi: 10.1109/JSTARS.2020.2966512 – ident: ref45 doi: 10.1109/TIP.2016.2627815 – ident: ref36 doi: 10.1109/TIP.2014.2314022 – ident: ref34 doi: 10.1109/TGRS.2008.918089 – ident: ref33 doi: 10.1109/TGRS.2018.2827407 – ident: ref4 doi: 10.1109/MSP.2013.2279731 – ident: ref3 doi: 10.1179/174313110X12771950995716 – ident: ref12 doi: 10.1126/science.260.5107.509 – ident: ref20 doi: 10.1109/TGRS.2018.2890633 – ident: ref18 doi: 10.1109/TGRS.2011.2160950 – ident: ref16 doi: 10.1109/TGRS.2018.2849692 – ident: ref29 doi: 10.1109/LGRS.2019.2900733 – ident: ref15 doi: 10.1109/TGRS.2016.2636241
SSID	ssj0057614
Score	2.5230083
Snippet	Blind hyperspectral unmixing is an important technique in hyperspectral image analysis, aiming at estimating endmembers and their respective fractional...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	295
SubjectTerms	Algorithms Artificial neural networks attention recurrent neural network autoencoder network Correlation Decoding Hyperspectral imaging Hyperspectral unmixing Image analysis Mathematical model Neural networks nonlinear unmixing Regularization Spectral correlation Task analysis Three-dimensional displays
Title	LSTM-DNN Based Autoencoder Network for Nonlinear Hyperspectral Image Unmixing
URI	https://ieeexplore.ieee.org/document/9326377 https://www.proquest.com/docview/2493604407
Volume	15
WOSCitedRecordID	wos000622098600012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0484 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0057614 issn: 1932-4553 databaseCode: RIE dateStart: 20070101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8QwFH6oeNCDuzg6Sg7eNNo2TZMc3QaFmSK44K00S2HAmZHOjPjzfWk7g6II3npIHuV7eVvyFoDjArWetYrTogg4jQtpqTKWUyEdWjuTy7xKonnuijSVLy_qfgFO57Uwzrkq-cyd-c_qLd-OzNRflZ17X4MJsQiLQiR1rdZM66LbHDYvyBGNOWezAplAneMRf7jHUDAKz5i_BU3Cb0aomqryQxVX9qWz_r8_24C1xo8kFzXjN2HBDbdg9Ut3wW3odR8ee_Q6TcklmipLLqaTkW9baV1J0jr7m6DLStK6W0ZeklsMSuvayxJp3w1Q15Cn4aD_gfR24Klz83h1S5vpCdREik-oCzHgVDHT_qXMouQVHvw4l9oyxXJmudCIGculYVIqHXIXC5ZYnWstuI7ZLiwNR0O3B0RK43ELbaCjWFsnE5Rc9AS1iQLNi7AF4QzOzDStxf2Ei9esCjEClVUsyDwLsoYFLTiZ73mrG2v8uXrbgz5f2eDdgvaMa1kje-MMA0qW-EnaYv_3XQew4mnXuddtWJqUU3cIy-Z90h-XR9Wx-gT3CMhR
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8NAFH64gXpwF-s6B286NsnMNDNHVyq2QbCKt5BZAoK2Elvx5_smSYuiCN5ymCV8b-Yt8zaAwxy5nrVK0DwPBOW5tFQZK2gsHUo7k8msDKJ56MRJIh8f1e0UHE9yYZxzZfCZO_GfpS_fDszIP5U1va7B4ngaZgXnUVBla435LirOYe1DjigXgo1TZALVxEN-d4vGYBSeMP8O2gq_iaGyr8oPZlxKmKvl__3bCizVmiQ5rUi_ClOuvwaLX-oLrkO3c9fr0oskIWcorCw5HQ0HvnCldQVJqvhvgkorSap6GVlB2miWVtmXBa59_YLchtz3X54-cL0NuL-67J23ad0_gZpIiSF1IZqcijPtfWUW717u4eeZ1JYpljErYo2YsUwaJqXSoXA8Zi2rM61joTnbhJn-oO-2gEhpPG6hDXTEtXWyhXcXdUFtokCLPGxAOIYzNXVxcd_j4jktjYxApSUJUk-CtCZBA44mc16r0hp_jl73oE9G1ng3YHdMtbS-fW8pmpSs5Xtpx9u_zzqA-Xav20k718nNDiz4fapI7F2YGRYjtwdz5n349Fbsl0fsE5A2y5g
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=LSTM-DNN+Based+Autoencoder+Network+for+Nonlinear+Hyperspectral+Image+Unmixing&rft.jtitle=IEEE+journal+of+selected+topics+in+signal+processing&rft.au=Zhao%2C+Min&rft.au=Yan%2C+Longbin&rft.au=Chen%2C+Jie&rft.date=2021-02-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1932-4553&rft.eissn=1941-0484&rft.volume=15&rft.issue=2&rft.spage=295&rft_id=info:doi/10.1109%2FJSTSP.2021.3052361&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4553&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4553&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4553&client=summon