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

Evaluation of clustering algorithms for unsupervised change detection in VHR remote sensing imagery

Leichtle, Tobias and Geiß, Christian and Wurm, Michael and Lakes, Tobia and Taubenböck, Hannes (2017) Evaluation of clustering algorithms for unsupervised change detection in VHR remote sensing imagery. In: 2017 Joint Urban Remote Sensing Event (JURSE), pp. 1-4. IEEE Xplore. Joint Urban Remote Sensing Event (JURSE) 2017, 06. Mär. - 08. Mär. 2017, Dubai, UAE. DOI: 10.1109/JURSE.2017.7924625 ISBN 978-1-5090-5808-2

This is the latest version of this item.

[img] PDF
972kB

Official URL: http://ieeexplore.ieee.org/document/7924625/

Abstract

Remote sensing has proven to be an adequate tool for observation of changes to the Earth’s surface. Especially modern space-borne sensors with very-high spatial resolution offer new capabilities for monitoring of dynamic urban environments. In this context, clustering is a well suited technique for unsupervised and thus highly automatic detection of changes. In this study, seven partitioning clustering algorithms from different methodological categories are evaluated regarding their suitability for unsupervised change detection. In addition, object-based feature sets of different characteristics are included in the analysis assessing their discriminative power for classification of changed against unchanged buildings. In general, the most important property of favorable algorithms is that they do not require additional arbitrary input parameters except the number of clusters. Best results were achieved based on the clustering algorithms k-means, partitioning around medoids, genetic k-means and self-organizing map clustering with accuracies in terms of κ statistics of 0.8 to 0.9 and beyond.

Item URL in elib:https://elib.dlr.de/111485/
Document Type:Conference or Workshop Item (Poster)
Title:Evaluation of clustering algorithms for unsupervised change detection in VHR remote sensing imagery
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Leichtle, Tobiastobias.leichtle (at) slu-web.deUNSPECIFIED
Geiß, ChristianChristian.Geiss (at) dlr.deUNSPECIFIED
Wurm, Michaelmichael.wurm (at) dlr.dehttps://orcid.org/0000-0001-5967-1894
Lakes, Tobiatobia.lakes (at) geo.hu-berlin.deUNSPECIFIED
Taubenböck, HannesHannes.Taubenboeck (at) dlr.deUNSPECIFIED
Date:2017
Journal or Publication Title:2017 Joint Urban Remote Sensing Event (JURSE)
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI :10.1109/JURSE.2017.7924625
Page Range:pp. 1-4
Publisher:IEEE Xplore
Series Name:2017 Joint Urban Remote Sensing Event (JURSE)
ISBN:978-1-5090-5808-2
Status:Published
Keywords:change detection; clustering; object-based image analysis; very-high resolution (VHR) remote sensing
Event Title:Joint Urban Remote Sensing Event (JURSE) 2017
Event Location:Dubai, UAE
Event Type:international Conference
Event Dates:06. Mär. - 08. Mär. 2017
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 - Vorhaben Zivile Kriseninformation und Georisiken (old)
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Geo Risks and Civil Security
German Remote Sensing Data Center > Land Surface
Deposited By: Leichtle, Tobias
Deposited On:27 Mar 2017 14:37
Last Modified:31 Jul 2019 20:08

Available Versions of this Item

  • Evaluation of clustering algorithms for unsupervised change detection in VHR remote sensing imagery. (deposited 27 Mar 2017 14:37) [Currently Displayed]

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.