Repository logo
 
Publication

Parallel hyperspectral unmixing method via split augmented lagrangian on GPU

2016-05Journal article Restricted access
Simple item page
dc.contributor.authorSevilla, Jorge
dc.contributor.authorMartin, Gabriel
dc.contributor.authorNascimento, Jose
dc.date.accessioned2016-05-02T11:00:19Z
dc.date.available2016-05-02T11:00:19Z
dc.date.issued2016-05
dc.description.abstractOne of the main problems of hyperspectral data analysis is the presence of mixed pixels due to the low spatial resolution of such images. Linear spectral unmixing aims at inferring pure spectral signatures and their fractions at each pixel of the scene. The huge data volumes acquired by hyperspectral sensors put stringent requirements on processing and unmixing methods. This letter proposes an efficient implementation of the method called simplex identification via split augmented Lagrangian (SISAL) which exploits the graphics processing unit (GPU) architecture at low level using Compute Unified Device Architecture. SISAL aims to identify the endmembers of a scene, i.e., is able to unmix hyperspectral data sets in which the pure pixel assumption is violated. The proposed implementation is performed in a pixel-by-pixel fashion using coalesced accesses to memory and exploiting shared memory to store temporary data. Furthermore, the kernels have been optimized to minimize the threads divergence, therefore achieving high GPU occupancy. The experimental results obtained for the simulated and real hyperspectral data sets reveal speedups up to 49 times, which demonstrates that the GPU implementation can significantly accelerate the method's execution over big data sets while maintaining the methods accuracy.pt_PT
dc.identifier.citationSEVILLA, Jorge; [et al] - Parallel hyperspectral unmixing method via split augmented lagrangian on GPU. IEEE Geoscience and Remote Sensing Letters. ISSN 1545-598X. Vol. 13, N.º 5 (2016), pp. 626-630pt_PT
dc.identifier.doi10.1109/LGRS.2016.2522561pt_PT
dc.identifier.issn1545-598X
dc.identifier.issn1558-0571
dc.identifier.urihttp://hdl.handle.net/10400.21/6137
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherIEEE - Institute of Electrical and Electronics Engineers Inc.pt_PT
dc.relationBeyond Convexity: Non-Convex Optimization and Game-Theoretic Approaches for Imaging Inverse Problems
dc.subjectGraphics processing unitspt_PT
dc.subjectGPUpt_PT
dc.subjectHyperspectral endmember extractionpt_PT
dc.subjectOnboard processingpt_PT
dc.subjectSimplex identification via split augmented Lagrangianpt_PT
dc.subjectSISALpt_PT
dc.titleParallel hyperspectral unmixing method via split augmented lagrangian on GPUpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleBeyond Convexity: Non-Convex Optimization and Game-Theoretic Approaches for Imaging Inverse Problems
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/UID%2FEEA%2F50008%2F2013/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FEEI-PRO%2F1470%2F2012/PT
oaire.citation.endPage630pt_PT
oaire.citation.issue5pt_PT
oaire.citation.startPage626pt_PT
oaire.citation.titleIEEE Geoscience and Remote Sensing Letterspt_PT
oaire.citation.volume13pt_PT
oaire.fundingStream5876
oaire.fundingStream3599-PPCDT
person.familyNameNascimento
person.givenNameJose
person.identifier.ciencia-id6912-6F61-1964
person.identifier.orcid0000-0002-5291-6147
person.identifier.ridE-6212-2015
person.identifier.scopus-author-id55920018000
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsclosedAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationc7ffc6c0-1bdc-4f47-962a-a90dfb03073c
relation.isAuthorOfPublication.latestForDiscoveryc7ffc6c0-1bdc-4f47-962a-a90dfb03073c
relation.isProjectOfPublicatione2d2f1f5-1327-45b3-954c-2fdc843270e7
relation.isProjectOfPublicationf85a60e7-ec58-4ed3-922c-fd82e40c1b13
relation.isProjectOfPublication.latestForDiscoverye2d2f1f5-1327-45b3-954c-2fdc843270e7

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Parallel hyperspectral unmixing method via split augmented lagrangian on GPU.pdf
Size:
1009.79 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Artigos