Parallel Hyperspectral Unmixing on GPUs

被引：34

作者：

Nascimento, Jose M. P. ^{[1
,2
]}

Bioucas-Dias, Jose M. ^{[1
,3
]}

Rodriguez Alves, Jose M. ^{[1
]}

Silva, Vitor ^{[4
]}

Plaza, Antonio ^{[5
]}

机构：

[1] Inst Telecomunicacoes, P-1049001 Lisbon, Portugal

[2] Inst Super Engn Lisboa, P-1959007 Lisbon, Portugal

[3] Univ Tecn Lisboa, Inst Super Tecn, P-2744016 Lisbon, Portugal

[4] Univ Coimbra, Inst Telecommun, Dept Engn Elect & Comp, P-3030290 Coimbra, Portugal

[5] Univ Extremadura, Hyperspectral Comp Lab, Caceres 06006, Spain

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2014年 / 11卷 / 03期

关键词：

Graphics processing unit (GPU); parallel methods; sparse unmixing by variable splitting and augmented Lagrangian (SUNSAL); unsupervised hyperspectral unmixing; vertex component analysis (VCA); VERTEX COMPONENT ANALYSIS; ENDMEMBER EXTRACTION; ALGORITHM;

D O I：

10.1109/LGRS.2013.2274328

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

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.

引用

页码：666 / 670

页数：5

共 50 条

[1] A parallel unmixing algorithm for hyperspectral images
Robila, Stefan A.
Maciak, Lukasz G.
[J]. INTELLIGENT ROBOTS AND COMPUTER VISION XXIV: ALGORITHMS, TECHNIQUES, AND ACTIVE VISION, 2006, 6384
[2] PARALLEL SPARSE UNMIXING OF HYPERSPECTRAL DATA
Rodriguez Alves, Jose M.
Nascimento, Jose M. P.
Bioucas-Dias, Jose M.
Plaza, Antonio
Silva, Vitor
[J]. 2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2013, : 1446 - 1449
[3] Hyperspectral Unmixing on GPUs and Multi-Core Processors: A Comparison
Bernabe, Sergio
Sanchez, Sergio
Plaza, Antonio
Lopez, Sebastian
Benediktsson, Jon Atli
Sarmiento, Roberto
[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2013, 6 (03) : 1386 - 1398
[4] Sparse Non-negative Matrix Factorization on GPUs for Hyperspectral Unmixing
Wu, Zebin
Ye, Shun
Liu, Jianjun
Sun, Le
Wei, Zhihui
[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (08) : 3640 - 3649
[5] Parallel Method for Sparse Semisupervised Hyperspectral Unmixing
Nascimento, Jose M. P.
Rodriguez Alves, Jose M.
Plaza, Antonio
Silva, Vitor
Bioucas-Dias, Jose M.
[J]. HIGH-PERFORMANCE COMPUTING IN REMOTE SENSING III, 2013, 8895
[6] Hyperspectral Parallel Image Compression on Edge GPUs
Ferraz, Oscar
Silva, Vitor
Falcao, Gabriel
[J]. REMOTE SENSING, 2021, 13 (06) : 1 - 13
[7] Fast determination of the number of endmembers for real-time hyperspectral unmixing on GPUs
Sanchez, Sergio
Plaza, Antonio
[J]. JOURNAL OF REAL-TIME IMAGE PROCESSING, 2014, 9 (03) : 397 - 405
[8] Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs
Sanchez, Sergio
Ramalho, Rui
Sousa, Leonel
Plaza, Antonio
[J]. JOURNAL OF REAL-TIME IMAGE PROCESSING, 2015, 10 (03) : 469 - 483
[9] Fast determination of the number of endmembers for real-time hyperspectral unmixing on GPUs
Sergio Sánchez
Antonio Plaza
[J]. Journal of Real-Time Image Processing, 2014, 9 : 397 - 405
[10] Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs
Sergio Sánchez
Rui Ramalho
Leonel Sousa
Antonio Plaza
[J]. Journal of Real-Time Image Processing, 2015, 10 : 469 - 483

← 1 2 3 4 5 →