File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Conditional mixed-state model for structural change analysis from very high resolution optical images

TitleConditional mixed-state model for structural change analysis from very high resolution optical images
Authors
KeywordsChange detection
Conditional random fields
Image analysis
Mixed-state model
Remote sensing
Issue Date2009
Citation
International Geoscience And Remote Sensing Symposium (Igarss), 2009, v. 2, p. II988-II991 How to Cite?
AbstractThe present work concerns the analysis of dynamic scenes from earth observation images. We are interested in building a map which, on one hand locates places of change, on the other hand, reconstructs a unique visual information of the non-change areas. We show in this paper that such a problem can naturally be takled with conditional mixed-state random field modeling (mixed-state CRF), where the "mixed state" refers to the symbolic or continous nature of the unknown variable. The maximum a posteriori (MAP) estimation of the CRF is, through the Hammersley-Clifford theorem, turned into an energy minimisation problem. We tested the model on several Quickbird images and illustrate the quality of the results. ©2009 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/132604
References

 

DC FieldValueLanguage
dc.contributor.authorBelmudez, Ben_HK
dc.contributor.authorPrinet, Ven_HK
dc.contributor.authorYao, JFen_HK
dc.contributor.authorBouthemy, Pen_HK
dc.contributor.authorDescombes, Xen_HK
dc.date.accessioned2011-03-28T09:26:57Z-
dc.date.available2011-03-28T09:26:57Z-
dc.date.issued2009en_HK
dc.identifier.citationInternational Geoscience And Remote Sensing Symposium (Igarss), 2009, v. 2, p. II988-II991en_HK
dc.identifier.urihttp://hdl.handle.net/10722/132604-
dc.description.abstractThe present work concerns the analysis of dynamic scenes from earth observation images. We are interested in building a map which, on one hand locates places of change, on the other hand, reconstructs a unique visual information of the non-change areas. We show in this paper that such a problem can naturally be takled with conditional mixed-state random field modeling (mixed-state CRF), where the "mixed state" refers to the symbolic or continous nature of the unknown variable. The maximum a posteriori (MAP) estimation of the CRF is, through the Hammersley-Clifford theorem, turned into an energy minimisation problem. We tested the model on several Quickbird images and illustrate the quality of the results. ©2009 IEEE.en_HK
dc.languageengen_US
dc.relation.ispartofInternational Geoscience and Remote Sensing Symposium (IGARSS)en_HK
dc.subjectChange detectionen_HK
dc.subjectConditional random fieldsen_HK
dc.subjectImage analysisen_HK
dc.subjectMixed-state modelen_HK
dc.subjectRemote sensingen_HK
dc.titleConditional mixed-state model for structural change analysis from very high resolution optical imagesen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailYao, JF: jeffyao@hku.hken_HK
dc.identifier.authorityYao, JF=rp01473en_HK
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1109/IGARSS.2009.5418267en_HK
dc.identifier.scopuseid_2-s2.0-77951116538en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-77951116538&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume2en_HK
dc.identifier.spageII988en_HK
dc.identifier.epageII991en_HK
dc.identifier.scopusauthoridBelmudez, B=35309416700en_HK
dc.identifier.scopusauthoridPrinet, V=6603064670en_HK
dc.identifier.scopusauthoridYao, JF=7403503451en_HK
dc.identifier.scopusauthoridBouthemy, P=7005146506en_HK
dc.identifier.scopusauthoridDescombes, X=7004154987en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats