Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging

Jaime Zabalza, Chunmei Qing, Peter Yuen, Genyun Sun, Huimin Zhao, Jinchang Ren

Research output: Contribution to journalArticle

2 Citations (Scopus)
18 Downloads (Pure)

Abstract

Although singular spectrum analysis (SSA) has been successfully applied for data classification in hyperspectral remote sensing, it suffers from extremely high computational cost, especially for 2D-SSA. As a result, a fast implementation of 2D-SSA namely F-2D-SSA is presented in this paper, where the computational complexity has been significantly reduced with a rate up to 60%. From comprehensive experiments undertaken, the effectiveness of F-2D-SSA is validated producing a similar high-level of accuracy in pixel classification using support vector machine (SVM) classifier, yet with a much reduced complexity in comparison to conventional 2D-SSA. Therefore, the introduction and evaluation of F-2D-SSA completes a series of studies focused on SSA, where in this particular research, the reduction in computational complexity leads to potential applications in mobile and embedded devices such as airborne or satellite platforms.
Original languageEnglish
Number of pages19
JournalJournal of the Franklin Institute
Early online date12 May 2017
DOIs
Publication statusE-pub ahead of print - 12 May 2017

Fingerprint

Singular Spectrum Analysis
Hyperspectral Imaging
Data Classification
Spectrum analysis
Computational complexity
Computational Complexity
Hyperspectral Remote Sensing
Hyperspectral imaging
Support vector machines
Computational Cost
Remote sensing
Support Vector Machine
Classifiers
Pixel
Pixels
Classifier
Satellites

Keywords

  • data classification
  • fast 2-D singular spectrum analysis
  • hyperspectral imaging
  • land cover analysis
  • remote sensing

Cite this

@article{4a09aa1182ea4bc9b6e38dfe303dfb82,
title = "Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging",
abstract = "Although singular spectrum analysis (SSA) has been successfully applied for data classification in hyperspectral remote sensing, it suffers from extremely high computational cost, especially for 2D-SSA. As a result, a fast implementation of 2D-SSA namely F-2D-SSA is presented in this paper, where the computational complexity has been significantly reduced with a rate up to 60{\%}. From comprehensive experiments undertaken, the effectiveness of F-2D-SSA is validated producing a similar high-level of accuracy in pixel classification using support vector machine (SVM) classifier, yet with a much reduced complexity in comparison to conventional 2D-SSA. Therefore, the introduction and evaluation of F-2D-SSA completes a series of studies focused on SSA, where in this particular research, the reduction in computational complexity leads to potential applications in mobile and embedded devices such as airborne or satellite platforms.",
keywords = "data classification, fast 2-D singular spectrum analysis, hyperspectral imaging, land cover analysis, remote sensing",
author = "Jaime Zabalza and Chunmei Qing and Peter Yuen and Genyun Sun and Huimin Zhao and Jinchang Ren",
year = "2017",
month = "5",
day = "12",
doi = "10.1016/j.jfranklin.2017.05.020",
language = "English",
journal = "Journal of the Franklin Institute",
issn = "0016-0032",

}

Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging. / Zabalza, Jaime; Qing, Chunmei; Yuen, Peter; Sun, Genyun; Zhao, Huimin; Ren, Jinchang.

In: Journal of the Franklin Institute, 12.05.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging

AU - Zabalza, Jaime

AU - Qing, Chunmei

AU - Yuen, Peter

AU - Sun, Genyun

AU - Zhao, Huimin

AU - Ren, Jinchang

PY - 2017/5/12

Y1 - 2017/5/12

N2 - Although singular spectrum analysis (SSA) has been successfully applied for data classification in hyperspectral remote sensing, it suffers from extremely high computational cost, especially for 2D-SSA. As a result, a fast implementation of 2D-SSA namely F-2D-SSA is presented in this paper, where the computational complexity has been significantly reduced with a rate up to 60%. From comprehensive experiments undertaken, the effectiveness of F-2D-SSA is validated producing a similar high-level of accuracy in pixel classification using support vector machine (SVM) classifier, yet with a much reduced complexity in comparison to conventional 2D-SSA. Therefore, the introduction and evaluation of F-2D-SSA completes a series of studies focused on SSA, where in this particular research, the reduction in computational complexity leads to potential applications in mobile and embedded devices such as airborne or satellite platforms.

AB - Although singular spectrum analysis (SSA) has been successfully applied for data classification in hyperspectral remote sensing, it suffers from extremely high computational cost, especially for 2D-SSA. As a result, a fast implementation of 2D-SSA namely F-2D-SSA is presented in this paper, where the computational complexity has been significantly reduced with a rate up to 60%. From comprehensive experiments undertaken, the effectiveness of F-2D-SSA is validated producing a similar high-level of accuracy in pixel classification using support vector machine (SVM) classifier, yet with a much reduced complexity in comparison to conventional 2D-SSA. Therefore, the introduction and evaluation of F-2D-SSA completes a series of studies focused on SSA, where in this particular research, the reduction in computational complexity leads to potential applications in mobile and embedded devices such as airborne or satellite platforms.

KW - data classification

KW - fast 2-D singular spectrum analysis

KW - hyperspectral imaging

KW - land cover analysis

KW - remote sensing

UR - http://www.sciencedirect.com/science/article/pii/S0016003217302430

U2 - 10.1016/j.jfranklin.2017.05.020

DO - 10.1016/j.jfranklin.2017.05.020

M3 - Article

JO - Journal of the Franklin Institute

JF - Journal of the Franklin Institute

SN - 0016-0032

ER -