Parallel Hyperspectral Unmixing on GPUs

Author

Nascimento, Jose M. P. ; Bioucas-Dias, Jose M. ; Rodriguez Alves, Jose M. ; Silva, Valter ; Plaza, Antonio

Author_Institution

Inst. de Telecomun., Lisbon, Portugal

Volume

11

Issue

3

fYear

2014

fDate

Mar-14

Firstpage

666

Lastpage

670

Abstract

This letter presents a new parallel method for hyperspectral unmixing composed by the efficient combination of two popular methods: vertex component analysis (VCA) and sparse unmixing by variable splitting and augmented Lagrangian (SUNSAL). First, VCA extracts the endmember signatures, and then, SUNSAL is used to estimate the abundance fractions. Both techniques are highly parallelizable, which significantly reduces the computing time. A design for the commodity graphics processing units of the two methods is presented and evaluated. Experimental results obtained for simulated and real hyperspectral data sets reveal speedups up to 100 times, which grants real-time response required by many remotely sensed hyperspectral applications.

Keywords

graphics processing units; hyperspectral imaging; image processing; remote sensing; GPU; SUNSAL; VCA; abundance fraction estimation; augmented Lagrangian; endmember signature extraction; graphics processing unit; parallel hyperspectral unmixing; sparse unmixing by variable splitting; vertex component analysis; Graphics processing units; Hyperspectral imaging; Instruction sets; Kernel; Vectors; Graphics processing unit (GPU); parallel methods; sparse unmixing by variable splitting and augmented Lagrangian (SUNSAL); unsupervised hyperspectral unmixing; vertex component analysis (VCA);

fLanguage

English

Journal_Title

Geoscience and Remote Sensing Letters, IEEE

Publisher

ieee

ISSN

1545-598X

Type

jour

DOI

10.1109/LGRS.2013.2274328

Filename

6605525