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

A Three-class Change Detection Methodology for SAR-data based on Hypothesis Testing and Markov Random Field Modeling

Cao, Wenxi and Twele, Andre and Plank, Simon Manuel and Martinis, Sandro (2017) A Three-class Change Detection Methodology for SAR-data based on Hypothesis Testing and Markov Random Field Modeling. International Journal of Remote Sensing, 39 (2), pp. 488-504. Taylor & Francis. DOI: 10.1080/01431161.2017.1384590 ISSN 0143-1161

Full text not available from this repository.

Official URL: http://www.tandfonline.com/doi/abs/10.1080/01431161.2017.1384590

Abstract

This study presents a new automatic change detection process chain based on bi-temporal co-registered and calibrated Sentinel-1 level-1 Interferometric Wide (IW) Ground Range Detected (GRD) C-band Synthetic Aperture Radar (SAR) intensity imagery. The whole processor contains three main components: Firstly, a prepro- cessing step is used to perform geometrical and radiometrical calibration. Secondly, an automatic coarse detection step is applied based on a statistical hypothesis test to obtain an initial classifcation. Thirdly, a post-classifcation step is introduced to optimise the initial classifcation result in the form of minimising a global energy function de�ned on a Markov Random Field (MRF). In this study, a graph-cut algorithm is applied iteratively to solve the global optimisation problem. At each iteration, the data energy function for the current classification are set by the logarithmic probability density function (PDF). The relevant parameters are estimated by the method of logarithmic cumulants (MoLC). An appendix is presented at the end to explain the formulae used in this study. Experiments are performed using a good event which occurred in 2015 along the coastline of Greece near Kavala region and the Evros River at the border between Greece and Turkey. The proposed method shows a satisfying classifcation result with overall accuracy above 95% and kappa coefcient (�) above 0.87.

Item URL in elib:https://elib.dlr.de/114408/
Document Type:Article
Title:A Three-class Change Detection Methodology for SAR-data based on Hypothesis Testing and Markov Random Field Modeling
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Cao, WenxiWenxi.Cao (at) dlr.dehttps://orcid.org/0000-0001-9567-3053
Twele, AndreAndre.Twele (at) dlr.dehttps://orcid.org/0000-0002-8035-2625
Plank, Simon ManuelSimon.Plank (at) dlr.dehttps://orcid.org/0000-0002-5793-052X
Martinis, Sandrosandro.martinis (at) dlr.dehttps://orcid.org/0000-0002-6400-361X
Date:2017
Journal or Publication Title:International Journal of Remote Sensing
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:39
DOI :10.1080/01431161.2017.1384590
Page Range:pp. 488-504
Publisher:Taylor & Francis
ISSN:0143-1161
Status:Published
Keywords:Synthetic Aperture Radar (SAR), Disaster Monitoring, Markov Random Field (MRF), and Sentinel-1
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Remote sensing and geoscience
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Geo Risks and Civil Security
Deposited By: Cao, Wenxi
Deposited On:28 Sep 2017 14:09
Last Modified:08 Nov 2017 09:42

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.