Publication
GPU implementation of the simplex identification via split augmented Lagrangian
| dc.contributor.author | Sevilla, Jorge | |
| dc.contributor.author | Nascimento, Jose | |
| dc.date.accessioned | 2016-04-26T11:14:43Z | |
| dc.date.available | 2016-04-26T11:14:43Z | |
| dc.date.issued | 2015 | |
| dc.description.abstract | Hyperspectral imaging can be used for object detection and for discriminating between different objects based on their spectral characteristics. One of the main problems of hyperspectral data analysis is the presence of mixed pixels, due to the low spatial resolution of such images. This means that several spectrally pure signatures (endmembers) are combined into the same mixed pixel. Linear spectral unmixing follows an unsupervised approach which aims at inferring pure spectral signatures and their material fractions at each pixel of the scene. The huge data volumes acquired by such sensors put stringent requirements on processing and unmixing methods. This paper proposes an efficient implementation of a unsupervised linear unmixing method on GPUs using CUDA. The method finds the smallest simplex by solving a sequence of nonsmooth convex subproblems using variable splitting to obtain a constraint formulation, and then applying an augmented Lagrangian technique. The parallel implementation of SISAL presented in this work exploits the GPU architecture at low level, using shared memory and coalesced accesses to memory. The results herein presented indicate that the GPU implementation can significantly accelerate the method's execution over big datasets while maintaining the methods accuracy. | pt_PT |
| dc.identifier.citation | SEVILLA, Jorge; NASCIMENTO, José - GPU implementation of the simplex identification via split augmented Lagrangian. High-Performance Computing in Remote Sensing V. ISSN 0277-786X. 2015 | pt_PT |
| dc.identifier.doi | 10.1117/12.2194519 | pt_PT |
| dc.identifier.isbn | 978-1-62841-856-9 | |
| dc.identifier.issn | 0277-786X | |
| dc.identifier.uri | http://hdl.handle.net/10400.21/6087 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.publisher | SPIE-International Societe Optical Engineering | pt_PT |
| dc.relation | Beyond Convexity: Non-Convex Optimization and Game-Theoretic Approaches for Imaging Inverse Problems | |
| dc.relation | NEW HYPERSPECTRAL COMPRESSIVE SENSING AND UNMIXING FRAMEWORK. | |
| dc.relation.ispartofseries | Proceedings of SPIE;964607 | |
| dc.subject | Hyperspectral endmember extraction | pt_PT |
| dc.subject | Simplex Identification via Split Augmented Lagrangian | pt_PT |
| dc.subject | SISAL | pt_PT |
| dc.subject | Graphics Processing Units | pt_PT |
| dc.subject | GPU | pt_PT |
| dc.subject | Onboard processing | pt_PT |
| dc.title | GPU implementation of the simplex identification via split augmented Lagrangian | pt_PT |
| dc.type | conference object | |
| dspace.entity.type | Publication | |
| oaire.awardTitle | Beyond Convexity: Non-Convex Optimization and Game-Theoretic Approaches for Imaging Inverse Problems | |
| oaire.awardTitle | NEW HYPERSPECTRAL COMPRESSIVE SENSING AND UNMIXING FRAMEWORK. | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/5876/UID%2FEEA%2F50008%2F2013/PT | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FEEI-PRO%2F1470%2F2012/PT | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT//SFRH%2FBPD%2F94160%2F2013/PT | |
| oaire.citation.conferencePlace | Toulouse, France | pt_PT |
| oaire.citation.title | High-Performance Computing in Remote Sensing V | pt_PT |
| oaire.citation.volume | 9646 | pt_PT |
| oaire.fundingStream | 5876 | |
| oaire.fundingStream | 3599-PPCDT | |
| person.familyName | Nascimento | |
| person.givenName | Jose | |
| person.identifier.ciencia-id | 6912-6F61-1964 | |
| person.identifier.orcid | 0000-0002-5291-6147 | |
| person.identifier.rid | E-6212-2015 | |
| person.identifier.scopus-author-id | 55920018000 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| rcaap.rights | closedAccess | pt_PT |
| rcaap.type | conferenceObject | pt_PT |
| relation.isAuthorOfPublication | c7ffc6c0-1bdc-4f47-962a-a90dfb03073c | |
| relation.isAuthorOfPublication.latestForDiscovery | c7ffc6c0-1bdc-4f47-962a-a90dfb03073c | |
| relation.isProjectOfPublication | e2d2f1f5-1327-45b3-954c-2fdc843270e7 | |
| relation.isProjectOfPublication | f85a60e7-ec58-4ed3-922c-fd82e40c1b13 | |
| relation.isProjectOfPublication | e24a884a-f234-45c7-92b5-4df02ccdce9e | |
| relation.isProjectOfPublication.latestForDiscovery | e2d2f1f5-1327-45b3-954c-2fdc843270e7 |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- GPU IMPLEMENTATION OF A HYPERSPECTRAL CODED APERTURE ALGORITHM FOR COMPRESSIVE SENSING.pdf
- Size:
- 363.6 KB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: