Show simple item record

dc.contributor.authorAkçay, H. Gökhanen_US
dc.contributor.authorAksoy, Selimen_US
dc.coverage.spatialHonolulu, HI, USAen_US
dc.date.accessioned2016-02-08T12:21:31Z
dc.date.available2016-02-08T12:21:31Z
dc.date.issued2010en_US
dc.identifier.urihttp://hdl.handle.net/11693/28470
dc.descriptionDate of Conference: 25-30 July 2010en_US
dc.description.abstractWe propose an algorithm for automatic detection of buildings with complex shapes and roof structures in very high spatial resolution remotely sensed images. First, an initial oversegmentation is obtained. Then, candidate building regions are found using shadow and sun azimuth angle information. Finally, the building regions are selected by clustering the candidate regions using minimum spanning trees. The experiments on Ikonos scenes show that the algorithm is able to detect buildings with complex appearances and shapes. © 2010 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.title2010 IEEE International Geoscience and Remote Sensing Symposiumen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/IGARSS.2010.5652842en_US
dc.subjectBuilding detectionen_US
dc.subjectMinimum spanning treesen_US
dc.subjectSegmentationen_US
dc.subjectSpatial relationshipsen_US
dc.subjectAutomatic Detectionen_US
dc.subjectAzimuth anglesen_US
dc.subjectBuilding detectionen_US
dc.subjectComplex shapesen_US
dc.subjectMinimum spanning treesen_US
dc.subjectOver segmentationen_US
dc.subjectRemotely sensed imagesen_US
dc.subjectRoof structuresen_US
dc.subjectSegmentationen_US
dc.subjectSpatial constraintsen_US
dc.subjectSpatial relationshipsen_US
dc.subjectVery high spatial resolutionsen_US
dc.subjectAlgorithmsen_US
dc.subjectGeologyen_US
dc.subjectRemote sensingen_US
dc.subjectBuildingsen_US
dc.titleBuilding detection using directional spatial constraintsen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage1932en_US
dc.citation.epage1935en_US
dc.identifier.doi10.1109/IGARSS.2010.5652842en_US
dc.publisherIEEEen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record