Repository logo
 
Publication

Hyperspectral image reconstruction from random projections on GPU

2016-11-03Conference object Restricted access
Simple item page
dc.contributor.authorSevilla, Jorge
dc.contributor.authorMartin, Gabriel
dc.contributor.authorNascimento, Jose
dc.contributor.authorBioucas-Dias, José
dc.date.accessioned2019-03-01T09:20:59Z
dc.date.available2019-03-01T09:20:59Z
dc.date.issued2016-11-03
dc.description.abstractHyperspectral data compression and dimensionality reduction has received considerable interest in recent years due to the high spectral resolution of these images. Contrarily to the conventional dimensionality reduction schemes, the spectral compressive acquisition method (SpeCA) performs dimensionality reduction based on random projections. The SpeCA methodology has applications in Hyperspectral Compressive Sensing and also in dimensionality reduction. Due to the extremely large volumes of data collected by imaging spectrometers, high performance computing architectures are needed for data compression of high dimensional hyperspectral data under real-time constrained applications. In this paper a parallel implementation of SpeCA on Graphics Processing Units (GPUs) using the compute unified device architecture (CUDA) is proposed. 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 kemeIs have been optimized to minimize the threads divergence, therefore, achieving high GPU occupancy. The experimental results obtained for simulated and real hyperspectral data sets reveal speedups up to 21 tim es, which demonstrates that the GPU implementation can significantly accelerate the methods execution over big datasets while maintaining the methods accuracy.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationSEVILLA, Jorge; [et al] – Hyperspectral image reconstruction from random projections on GPU. In 36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Beijing, China: IEEE, 2016. ISBN 978-1-5090-3332-4. Pp. 280-283pt_PT
dc.identifier.doi10.1109/IGARSS.2016.7729064pt_PT
dc.identifier.isbn978-1-5090-3332-4
dc.identifier.isbn978-1-5090-3331-7
dc.identifier.isbn978-1-5090-3333-1
dc.identifier.issn2153-7003
dc.identifier.urihttp://hdl.handle.net/10400.21/9607
dc.language.isoengpt_PT
dc.publisherInstitute of Electrical and Electronics Engineerspt_PT
dc.relationUlD/EEA/50008/2013 - FCT e lnstituto de Telecomunicaçõespt_PT
dc.relationPTDC/EEI-PRO/1470/2012 - FCT e lnstituto de Telecomunicaçõespt_PT
dc.relationSFRH/BPD/94160/2013 - FCT e lnstituto de Telecomunicaçõespt_PT
dc.relation.publisherversionhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7729064&tag=1pt_PT
dc.subjectCompressing sensingpt_PT
dc.subjectDimensionality reductionpt_PT
dc.subjectGPUspt_PT
dc.subjectUnmixingpt_PT
dc.subjectHypespectralpt_PT
dc.subjectRemote sensingpt_PT
dc.titleHyperspectral image reconstruction from random projections on GPUpt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.citation.conferencePlace10-15 July 2016 - Beijing, Chinapt_PT
oaire.citation.endPage283pt_PT
oaire.citation.startPage280pt_PT
oaire.citation.title36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)pt_PT
person.familyNameNascimento
person.familyNameBioucas-Dias
person.givenNameJose
person.givenNameJosé
person.identifier.ciencia-id6912-6F61-1964
person.identifier.orcid0000-0002-5291-6147
person.identifier.orcid0000-0002-0166-5149
person.identifier.ridE-6212-2015
person.identifier.ridC-5479-2009
person.identifier.scopus-author-id55920018000
person.identifier.scopus-author-id55901520500
rcaap.rightsclosedAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicationc7ffc6c0-1bdc-4f47-962a-a90dfb03073c
relation.isAuthorOfPublication36373d86-2841-4499-8115-0639a9790a15
relation.isAuthorOfPublication.latestForDiscoveryc7ffc6c0-1bdc-4f47-962a-a90dfb03073c

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
JNascimento.pdf
Size:
2.76 MB
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. - Comunicações