Recent advances in techniques for hyperspectral image processing

被引：1288

作者：

Plaza, Antonio ^{[1
]}

Benediktsson, Jon Atli ^{[2
]}

Boardman, Joseph W. ^{[3
]}

Brazile, Jason ^{[4
]}

Bruzzone, Lorenzo ^{[5
]}

Camps-Valls, Gustavo ^{[6
]}

Chanussot, Jocelyn ^{[7
]}

Fauvel, Mathieu ^{[2
,7
]}

Gamba, Paolo ^{[8
]}

Gualtieri, Anthony ^{[9
,10
]}

Marconcini, Mattia ^{[5
]}

Tilton, James C. ^{[9
]}

Trianni, Giovanna ^{[8
]}

机构：

[1] Univ Extremadura, Dept Technol Comp & Commun, Caceres, Spain

[2] Univ Iceland, Fac Elect & Comp Engn, Reykjavik, Iceland

[3] Analyt Imaging & Geophys LLC, Boulder, CO USA

[4] Univ Zurich, Dept Geog, CH-8006 Zurich, Switzerland

[5] Univ Trent, Dept Comp Sci & Informat Engn, I-38100 Trento, Italy

[6] Univ Valencia, Dept Elect Engn, E-46003 Valencia, Spain

[7] Grenoble Inst Technol, GIPSA Lab, Grenoble, France

[8] Univ Pavia, Dept Elect, I-27100 Pavia, Italy

[9] NASA, Goddard Space Flight Ctr, Greenbelt, MD 20771 USA

[10] Global Sci & Technol, Greenbelt, MD USA

来源：

REMOTE SENSING OF ENVIRONMENT | 2009年 / 113卷

关键词：

Classification; Hyperspectral imaging; Kernel methods; Support vector machines; Markov random fields; Mathematical morphology; Spatial/spectral processing; Spectral mixture analysis; Endmember extraction; Parallel processing; REMOTE-SENSING IMAGES; SEMISUPERVISED CLASSIFICATION; ENDMEMBER EXTRACTION; SEGMENTATION; VEGETATION; DESERTS; MIXTURE; SVM;

D O I：

10.1016/j.rse.2007.07.028

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Imaging spectroscopy, also known as hyperspectral imaging, has been transformed in less than 30 years from being a sparse research tool into a commodity product available to a broad user community. Currently, there is a need for standardized data processing techniques able to take into account the special properties of hyperspectral data. In this paper, we provide a seminal view on recent advances in techniques for hyperspectral image processing. Our main focus is on the design of techniques able to deal with the high-dimensional nature of the data, and to integrate the spatial and spectral information. Performance of the discussed techniques is evaluated in different analysis scenarios. To satisfy time-critical constraints in specific applications, we also develop efficient parallel implementations of some of the discussed algorithms. Combined, these parts provide an excellent snapshot of the state-of-the-art in those areas. and offer a thoughtful perspective on future potentials and emerging challenges in the design of robust hyperspectral imaging algorithms. (C) 2009 Elsevier Inc. All rights reserved.

引用

页码：S110 / S122

页数：13

共 64 条

[1]

ADAMS JB, 1986, J GEOPHYS RES-SOLID, V91, P8098, DOI 10.1029/JB091iB08p08098

[2]

[Anonymous], 1999, REMOTE SENSING DIGIT

[3]

[Anonymous], 1982, IMAGE ANAL MATH MORP

[4]

[Anonymous], 1998, CLASSIFICATION HIGH

[5]

[Anonymous], P SPIE, DOI DOI 10.1117/12.339824

[6]

[Anonymous], 2003, WILEY HOBOKEN

[7]

[Anonymous], 1999, ADV KERNEL METHODS S

[8]

[Anonymous], 2003, Morphological Image Analysis: Principles and Applications

[9] Comparison of the multilayer perceptron with neuro-fuzzy techniques in the estimation of cover class mixture in remotely sensed data [J].

Baraldi, A ;

Binaghi, E ;

Blonda, P ;

Brivio, PA ;

Rampini, A .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (05) :994-1005

[10] HIERARCHY IN PICTURE SEGMENTATION - A STEPWISE OPTIMIZATION APPROACH [J].

BEAULIEU, JM ;

GOLDBERG, M .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (02) :150-163

← 1 2 3 4 5 6 7 →