Show simple item record

dc.contributor.authorAkçay, H. Gökhanen_US
dc.contributor.authorAksoy, Selimen_US
dc.coverage.spatialParis, France
dc.date.accessioned2016-02-08T11:44:04Z
dc.date.available2016-02-08T11:44:04Z
dc.date.issued2007-04en_US
dc.identifier.urihttp://hdl.handle.net/11693/27093
dc.descriptionDate of Conference: 11-13 April 2007
dc.descriptionConference name: 2007 Urban Remote Sensing Joint Event
dc.description.abstractAutomatic segmentation of high-resolution remote sensing imagery is an important problem in urban applications because the resulting segmentations can provide valuable spatial and structural information that are complementary to pixel-based spectral information in classification. We present a method that combines structural information extracted by morphological processing with spectral information summarized using principal components analysis to produce precise segmentations that are also robust to noise. First, principal components are computed from hyper-spectral data to obtain representative bands. Then, candidate regions are extracted by applying connected components analysis to the pixels selected according to their morphological profiles computed using opening and closing by reconstruction with increasing structuring element sizes. Next, these regions are represented using a tree, and the most meaningful ones are selected by optimizing a measure that consists of two factors: spectral homogeneity, which is calculated in terms of variances of spectral features, and neighborhood connectivity, which is calculated using sizes of connected components. The experiments show that the method is able to detect structures in the image which are more precise and more meaningful than the structures detected by another approach that does not make strong use of neighborhood and spectral information. © 2007 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.title2007 Urban Remote Sensing Joint Event, URSen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/URS.2007.371765en_US
dc.subjectMorphologyen_US
dc.subjectOptimizationen_US
dc.subjectRemote sensingen_US
dc.subjectSpectrum analysisen_US
dc.subjectAutomatic segmentationen_US
dc.subjectSpectral homogeneityen_US
dc.subjectUrban structuresen_US
dc.subjectImage segmentationen_US
dc.titleMorphological segmentation of urban structuresen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.identifier.doi10.1109/URS.2007.371765en_US
dc.publisherIEEE


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record