Show simple item record

dc.contributor.authorAkçay H. Gökhanen_US
dc.contributor.authorAksoy, Selimen_US
dc.coverage.spatialBarcelona, Spain
dc.date.accessioned2016-02-08T11:41:10Z
dc.date.available2016-02-08T11:41:10Z
dc.date.issued2007-07en_US
dc.identifier.urihttp://hdl.handle.net/11693/26981
dc.descriptionDate of Conference: 23-28 July 2007
dc.descriptionConference name: IEEE International Geoscience and Remote Sensing Symposium, 2007
dc.description.abstractWe introduce an unsupervised method that combines both spectral and structural information for automatic object detection. First, a segmentation hierarchy is constructed by combining structural information extracted by morphological processing with spectral information summarized using principal components analysis. Then, segments that maximize a measure consisting of spectral homogeneity and neighborhood connectivity are selected as candidate structures for object detection. Given the observation that different structures appear more clearly in different principal components, we present an algorithm that is based on probabilistic Latent Semantic Analysis (PLSA) for grouping the candidate segments belonging to multiple segmentations and multiple principal components. The segments are modeled using their spectral content and the PLSA algorithm builds object models by learning the object-conditional probability distributions. Labeling of a segment is done by computing the similarity of its spectral distribution to the distribution of object models using Kullback-Leibler divergence. Experiments on two data sets show that our method is able to automatically detect, group, and label segments belonging to the same object classes. © 2007 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.titleInternational Geoscience and Remote Sensing Symposium (IGARSS), 2007en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/IGARSS.2007.4423085en_US
dc.subjectAutomated detectionen_US
dc.subjectMultiple hierarchical segmentationsen_US
dc.subjectStructural informationen_US
dc.subjectAlgorithmsen_US
dc.subjectImage segmentationen_US
dc.subjectInformation disseminationen_US
dc.subjectProbabilityen_US
dc.subjectObject recognitionen_US
dc.titleAutomated detection of objects using multiple hierarchical segmentationsen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage1468en_US
dc.citation.epage1471en_US
dc.identifier.doi10.1109/IGARSS.2007.4423085en_US
dc.publisherIEEE


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record