Please use this identifier to cite or link to this item:
Title: A novel highly parallel algorithm for linearly unmixing hyperspectral images
Authors: Guerra, Raúl 
López, Sebastián 
Callico, Gustavo M. 
López Feliciano, José Francisco 
Sarmiento, Roberto 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Spectroscopy
Remote sensing
Endmember extraction
Issue Date: 2014
Publisher: 0277-786X
Journal: Proceedings of SPIE - The International Society for Optical Engineering 
Conference: Conference on High-Performance Computing in Remote Sensing IV 
Abstract: Endmember extraction and abundances calculation represent critical steps within the process of linearly unmixing a given hyperspectral image because of two main reasons. The first one is due to the need of computing a set of accurate endmembers in order to further obtain confident abundance maps. The second one refers to the huge amount of operations involved in these time-consuming processes. This work proposes an algorithm to estimate the endmembers of a hyperspectral image under analysis and its abundances at the same time. The main advantage of this algorithm is its high parallelization degree and the mathematical simplicity of the operations implemented. This algorithm estimates the endmembers as virtual pixels. In particular, the proposed algorithm performs the descent gradient method to iteratively refine the endmembers and the abundances, reducing the mean square error, according with the linear unmixing model. Some mathematical restrictions must be added so the method converges in a unique and realistic solution. According with the algorithm nature, these restrictions can be easily implemented. The results obtained with synthetic images demonstrate the well behavior of the algorithm proposed. Moreover, the results obtained with the well-known Cuprite dataset also corroborate the benefits of our proposal.
ISBN: 9781628413106
ISSN: 0277-786X
DOI: 10.1117/12.2068332
Source: Proceedings of SPIE - The International Society for Optical Engineering[ISSN 0277-786X],v. 9247 (92470H)
Appears in Collections:Actas de congresos
Show full item record

Page view(s)

checked on Feb 10, 2024

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.