File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Article: A matching algorithm for detecting land use changes using case-based reasoning
  • Basic View
  • Metadata View
  • XML View
TitleA matching algorithm for detecting land use changes using case-based reasoning
 
AuthorsXia, L3
Yeh, AGO1
Qian, JP3 2
Ai, B3
Qi, Z1
 
Issue Date2009
 
PublisherAmerican Society for Photogrammetry and Remote Sensing. The Journal's web site is located at http://www.asprs.org/publications/pers
 
CitationPhotogrammetric Engineering And Remote Sensing, 2009, v. 75 n. 11, p. 1319-1332 [How to Cite?]
 
AbstractThe paper deals with change detection using time series SAR images. SAR provides a unique opportunity for detecting land-use changes within short intervals (e.g., monthly) in tropical and sub-tropical regions with cloud cover. Traditional change detection methods mainly rely on per-pixel spectral information but ignore per-object structural information. In this study, a new method is presented that integrates object-oriented analysis with case-based reasoning (CBR) for change detection. Object-oriented analysis is carried out to retrieve a variety of features, such as tone, shape, texture, area, and context. An incremental segmentation technique is proposed for deriving change objects from multi-temporal Radarsat images. Feature selection based on genetic algorithms is carried out to determine the optimal set of features for change detection. A CBR matching algorithm is developed to identify the temporal positions and the kind of changes. It is based on the weighted k-Nearest Neighbor classification using an accumulative similarity measure. The comparison of the four combinations of change detection methods, object-based or pixel-based plus case-based or rule-based, is carried out to validate the performance of this proposed method. The analysis shows that this integrated approach has provided an efficient way of detecting land-use changes at monthly intervals by using multi-temporal SAR images. © 2009 American Society for Photogrammetry and Remote Sensing.
 
DescriptionThe article can be viewed at http://eserv.asprs.org/PERS/2009journal/nov/2009_nov_1319-1332.pdf
 
ISSN0099-1112
2012 Impact Factor: 1.802
2012 SCImago Journal Rankings: 0.883
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorXia, L
 
dc.contributor.authorYeh, AGO
 
dc.contributor.authorQian, JP
 
dc.contributor.authorAi, B
 
dc.contributor.authorQi, Z
 
dc.date.accessioned2010-10-31T13:36:50Z
 
dc.date.available2010-10-31T13:36:50Z
 
dc.date.issued2009
 
dc.description.abstractThe paper deals with change detection using time series SAR images. SAR provides a unique opportunity for detecting land-use changes within short intervals (e.g., monthly) in tropical and sub-tropical regions with cloud cover. Traditional change detection methods mainly rely on per-pixel spectral information but ignore per-object structural information. In this study, a new method is presented that integrates object-oriented analysis with case-based reasoning (CBR) for change detection. Object-oriented analysis is carried out to retrieve a variety of features, such as tone, shape, texture, area, and context. An incremental segmentation technique is proposed for deriving change objects from multi-temporal Radarsat images. Feature selection based on genetic algorithms is carried out to determine the optimal set of features for change detection. A CBR matching algorithm is developed to identify the temporal positions and the kind of changes. It is based on the weighted k-Nearest Neighbor classification using an accumulative similarity measure. The comparison of the four combinations of change detection methods, object-based or pixel-based plus case-based or rule-based, is carried out to validate the performance of this proposed method. The analysis shows that this integrated approach has provided an efficient way of detecting land-use changes at monthly intervals by using multi-temporal SAR images. © 2009 American Society for Photogrammetry and Remote Sensing.
 
dc.description.natureLink_to_subscribed_fulltext
 
dc.descriptionThe article can be viewed at http://eserv.asprs.org/PERS/2009journal/nov/2009_nov_1319-1332.pdf
 
dc.identifier.citationPhotogrammetric Engineering And Remote Sensing, 2009, v. 75 n. 11, p. 1319-1332 [How to Cite?]
 
dc.identifier.epage1332
 
dc.identifier.hkuros182888
 
dc.identifier.hkuros218399
 
dc.identifier.issn0099-1112
2012 Impact Factor: 1.802
2012 SCImago Journal Rankings: 0.883
 
dc.identifier.issue11
 
dc.identifier.scopuseid_2-s2.0-72449176358
 
dc.identifier.spage1319
 
dc.identifier.urihttp://hdl.handle.net/10722/127633
 
dc.identifier.volume75
 
dc.languageeng
 
dc.publisherAmerican Society for Photogrammetry and Remote Sensing. The Journal's web site is located at http://www.asprs.org/publications/pers
 
dc.publisher.placeUnited States
 
dc.relation.ispartofPhotogrammetric Engineering and Remote Sensing
 
dc.relation.referencesReferences in Scopus
 
dc.titleA matching algorithm for detecting land use changes using case-based reasoning
 
dc.typeArticle
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Xia, L</contributor.author>
<contributor.author>Yeh, AGO</contributor.author>
<contributor.author>Qian, JP</contributor.author>
<contributor.author>Ai, B</contributor.author>
<contributor.author>Qi, Z</contributor.author>
<date.accessioned>2010-10-31T13:36:50Z</date.accessioned>
<date.available>2010-10-31T13:36:50Z</date.available>
<date.issued>2009</date.issued>
<identifier.citation>Photogrammetric Engineering And Remote Sensing, 2009, v. 75 n. 11, p. 1319-1332</identifier.citation>
<identifier.issn>0099-1112</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/127633</identifier.uri>
<description>The article can be viewed at http://eserv.asprs.org/PERS/2009journal/nov/2009_nov_1319-1332.pdf</description>
<description.abstract>The paper deals with change detection using time series SAR images. SAR provides a unique opportunity for detecting land-use changes within short intervals (e.g., monthly) in tropical and sub-tropical regions with cloud cover. Traditional change detection methods mainly rely on per-pixel spectral information but ignore per-object structural information. In this study, a new method is presented that integrates object-oriented analysis with case-based reasoning (CBR) for change detection. Object-oriented analysis is carried out to retrieve a variety of features, such as tone, shape, texture, area, and context. An incremental segmentation technique is proposed for deriving change objects from multi-temporal Radarsat images. Feature selection based on genetic algorithms is carried out to determine the optimal set of features for change detection. A CBR matching algorithm is developed to identify the temporal positions and the kind of changes. It is based on the weighted k-Nearest Neighbor classification using an accumulative similarity measure. The comparison of the four combinations of change detection methods, object-based or pixel-based plus case-based or rule-based, is carried out to validate the performance of this proposed method. The analysis shows that this integrated approach has provided an efficient way of detecting land-use changes at monthly intervals by using multi-temporal SAR images. &#169; 2009 American Society for Photogrammetry and Remote Sensing.</description.abstract>
<language>eng</language>
<publisher>American Society for Photogrammetry and Remote Sensing. The Journal&apos;s web site is located at http://www.asprs.org/publications/pers</publisher>
<relation.ispartof>Photogrammetric Engineering and Remote Sensing</relation.ispartof>
<title>A matching algorithm for detecting land use changes using case-based reasoning</title>
<type>Article</type>
<description.nature>Link_to_subscribed_fulltext</description.nature>
<identifier.scopus>eid_2-s2.0-72449176358</identifier.scopus>
<identifier.hkuros>182888</identifier.hkuros>
<identifier.hkuros>218399</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-72449176358&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.volume>75</identifier.volume>
<identifier.issue>11</identifier.issue>
<identifier.spage>1319</identifier.spage>
<identifier.epage>1332</identifier.epage>
<publisher.place>United States</publisher.place>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Guangzhou Institute of Geography
  3. Sun Yat-Sen University