Using Hurst and Lyapunov Exponent For Hyperspectral Image Feature Extraction

被引：33

作者：

Yin, Jihao ^{[1
]}

Gao, Chao ^{[1
]}

Jia, Xiuping ^{[2
]}

机构：

[1] Beihang Univ, Sch Astronaut, Beijing 100191, Peoples R China

[2] Univ New S Wales, Australian Def Force Acad, Univ Coll, Sch Informat Technol & Elect Eng, Canberra, ACT 2600, Australia

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2012年 / 9卷 / 04期

基金：

中国国家自然科学基金; 高等学校博士学科点专项科研基金;

关键词：

Feature extraction; Hurst exponent; hyperspectral image; Lyapunov exponent; WEIGHTED FEATURE-EXTRACTION; DIMENSIONALITY REDUCTION;

D O I：

10.1109/LGRS.2011.2179005

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：

Hyperspectral image processing has attracted high attention in remote sensing fields. One of the main issues is to develop efficient methods for dimensionality reduction via feature extraction. This letter proposes a new nonlinear unsupervised feature extraction algorithm using Hurst and Lyapunov exponents to reveal local and general spectral profiles, respectively. A hyperspectral reflectance curve from each pixel is regarded as a time series, and it is represented by Hurst and Lyapunov exponents. These two new features are then used to overcome the Hughes problem for reliable classification. Experimental results show that the proposed method performs better than a few other feature extraction methods tested.

引用

页码：705 / 709

页数：5

共 29 条

[21]

LORENZ EN, 1963, J ATMOS SCI, V20, P130, DOI 10.1175/1520-0469(1963)020<0130:DNF>2.0.CO

[22]

[23] Using Suitable Neighbors to Augment the Training Set in Hyperspectral Maximum Likelihood Classification [J].

Richards, John A. ;

Jia, Xiuping .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2008, 5 (04) :774-777

[24] Validation of hyperspectral data classification models [J].

Semeniv, Oleg V. ;

Shatokhina, Yuliya V. ;

Yatsenko, Vitaliy A. .

Journal of Automation and Information Sciences, 2008, 40 (05) :46-51

[25] Signal processing for hyperspectral image exploitation [J].

Shaw, G ;

Manolakis, D .

IEEE SIGNAL PROCESSING MAGAZINE, 2002, 19 (01) :12-16

[26] The effectiveness of spectral similarity measures for the analysis of hyperspectral imagery [J].

van der Meer, F .

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2006, 8 (01) :3-17

[27]

Van der Meer F., 2004, Int J Appl Earth Obs., V5, P55, DOI [10.1016/j.jag.2003.09.001, DOI 10.1016/J.JAG.2003.09.001]

[28] A novel geometry-based feature-selection technique for hyperspectral imagery [J].

Wang, Liguo ;

Jia, Xiuping ;

Zhang, Ye .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2007, 4 (01) :171-175

[29] DETERMINING LYAPUNOV EXPONENTS FROM A TIME-SERIES [J].

WOLF, A ;

SWIFT, JB ;

SWINNEY, HL ;

VASTANO, JA .

PHYSICA D, 1985, 16 (03) :285-317

← 1 2 3 →