elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Assessing the performance of multiple spectral–spatial features of a hyperspectral image for classification of urban land cover classes using support vector machines and artificial neural network

Pullanagari, Reddy and Kereszturi, Gabor and Yule, Ian and Ghamisi, Pedram (2017) Assessing the performance of multiple spectral–spatial features of a hyperspectral image for classification of urban land cover classes using support vector machines and artificial neural network. Journal of Applied Remote Sensing, 11 (2), pp. 1-22. Society of Photo-optical Instrumentation Engineers (SPIE). doi: 10.1117/1.JRS.11.026009. ISSN 1931-3195.

[img] PDF
1MB

Official URL: http://remotesensing.spiedigitallibrary.org/article.aspx?articleid=2623136

Abstract

Accurate and spatially detailed mapping of complex urban environments is essential for land managers. Classifying high spectral and spatial resolution hyperspectral images is a challenging task because of its data abundance and computational complexity. Approaches witha combination of spectral and spatial information in a single classification framework haveattracted special attention because of their potential to improve the classification accuracy.We extracted multiple features from spectral and spatial domains of hyperspectral images and evaluated them with two supervised classification algorithms; support vector machines(SVM) and an artificial neural network. The spatial features considered are produced by agray level co-occurrence matrix and extended multiattribute profiles. All of these features were stacked, and the most informative features were selected using a genetic algorithm-based SVM. After selecting the most informative features, the classification model was integrated with a segmentation map derived using a hidden Markov random field. We tested the proposed method on a real application of a hyperspectral image acquired from AisaFENIX and on widely used hyperspectral images. From the results, it can be concluded that the proposed framework significantly improves the results with different spectral and spatial resolutions over different instrumentation.

Item URL in elib:https://elib.dlr.de/112013/
Document Type:Article
Title:Assessing the performance of multiple spectral–spatial features of a hyperspectral image for classification of urban land cover classes using support vector machines and artificial neural network
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Pullanagari, ReddyInstitute of Agriculture and Environment (IAE), Palmerston North, New ZealandUNSPECIFIED
Kereszturi, GaborInstitute of Agriculture and Environment (IAE), Palmerston North, New ZealandUNSPECIFIED
Yule, IanInstitute of Agriculture and Environment (IAE), Palmerston North, New ZealandUNSPECIFIED
Ghamisi, Pedramdlr-imf/tum-lmfUNSPECIFIED
Date:2017
Journal or Publication Title:Journal of Applied Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:11
DOI :10.1117/1.JRS.11.026009
Page Range:pp. 1-22
Editors:
EditorsEmailEditor's ORCID iD
Chang, Ni-BinUniversity of Central Florida, FL, USAUNSPECIFIED
Publisher:Society of Photo-optical Instrumentation Engineers (SPIE)
ISSN:1931-3195
Status:Published
Keywords:hyperspectral; classification; multiple features; gray level co-occurrence matrix;extended multiattribute profiles
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > SAR Signal Processing
Deposited By: Ghamisi, Pedram
Deposited On:26 Apr 2017 10:37
Last Modified:31 Jul 2019 20:09

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.