HYPERSPECTRAL IMAGE CLASSIFICATION USING BAND SELECTION AND MORPHOLOGICAL PROFILE

被引：0

作者：

Tan, Kun ^{[1
]}

Li, Erzhu ^{[1
]}

Du, Qian ^{[2
]}

Du, Peijun ^{[3
]}

机构：

[1] China Univ Min & Technol, Jiangsu Key Lab Resources & Environm Informat Eng, Beijing, Peoples R China

[2] Mississippi State Univ, Dept Elect & Comp Engn, Mississippi State, MS USA

[3] Nanjing Univ, Dept Geog Informat Sci, Nanjing, Peoples R China

来源：

2012 4TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING (WHISPERS) | 2012年

关键词：

Hyperspectral imaging; classification; band selection; morphological profile; dimensionality reduction;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we propose a new methodology to combine spectral information and spatial features for Support Vector Machine (SVM)-based classification. The novelty of the proposed work is in the combination of band selection (i.e., linear prediction (LP)-based method), spatial feature extraction (i.e., morphology profiles (MP)), and spectral transformation (i.e., principal component analysis (PCA)) to build a computationally tractable system. The preliminary result with ROSIS data shows that using the selected bands and MP features extracted from principal components (PCs) can yield the highest accuracy. We believe such finding is instructive to feature extraction/selection for spectral/spatial-based hyperspectral image classification.

引用

页数：4

共 21 条

[1]

[Anonymous], 1998, STAT LEARNING THEORY

[2] Classification of hyperspectral data from urban areas based on extended morphological profiles [J].

Benediktsson, JA ;

Palmason, JA ;

Sveinsson, JR .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :480-491

[3] Composite kernels for hyperspectral image classification [J].

Camps-Valls, G ;

Gomez-Chova, L ;

Muñoz-Marí, J ;

Vila-Francés, J ;

Calpe-Maravilla, J .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (01) :93-97

[4] Phase correlation based redundancy removal in feature weighting band selection for hyperspectral images [J].

Demir, B. ;

Erturk, S. .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 2008, 29 (06) :1801-1807

[5] Semi-supervised linear spectral unmixing using a hierarchical Bayesian model for hyperspectral imagery [J].

Dobigeon, Nicolas ;

Tourneret, Jean-Yves ;

Chang, Chein-I .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2008, 56 (07) :2684-2695

[6] Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis [J].

Du, Qian ;

Yang, He .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2008, 5 (04) :564-568

[7] Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles [J].

Fauvel, Mathieu ;

Benediktsson, Jon Atli ;

Chanussot, Jocelyn ;

Sveinsson, Johannes R. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (11) :3804-3814

[8] The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM [J].

Foody, Giles M. ;

Mathur, Ajay .

REMOTE SENSING OF ENVIRONMENT, 2006, 103 (02) :179-189

[9] Visual Method for Spectral Band Selection [J].

Ifarraguerri, Agustin ;

Prairie, Michael W. .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2004, 1 (02) :101-106

[10] Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries [J].

Keshava, N .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2004, 42 (07) :1552-1565

← 1 2 3 →