Land cover classification with multi-sensor fusion of partly missing data

Simple item page
dc.citation.epage593en_US
dc.citation.issueNumber5en_US
dc.citation.spage577en_US
dc.citation.volumeNumber75en_US
dc.contributor.authorAksoy, S.en_US
dc.contributor.authorKoperski, K.en_US
dc.contributor.authorTusk, C.en_US
dc.contributor.authorMarchisio, G.en_US
dc.date.accessioned2016-02-08T10:04:30Z
dc.date.available2016-02-08T10:04:30Z
dc.date.issued2009-05en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractWe describe a system that uses decision tree-based tools for seamless acquisition of knowledge for classification of remotely sensed imagery. We concentrate on three important problems in this process: information fusion, model understandability, and handling of missing data. Importance of multi-sensor information fusion and the use of decision tree classifiers for such problems have been well-studied in the literature. However, these studies have been limited to the cases where all data sources have a full coverage for the scene under consideration. Our contribution in this paper is to show how decision tree classifiers can be learned with alternative (surrogate) decision nodes and result in models that are capable of dealing with missing data during both training and classification to handle cases where one or more measurements do not exist for some locations. We present detailed performance evaluation regarding the effectiveness of these classifiers for information fusion and feature selection, and study three different methods for handling missing data in comparative experiments. The results show that surrogate decisions incorporated into decision tree classifiers provide powerful models for fusing information from different data layers while being robust to missing data. © 2009 American Society for Photogrammetry and Remote Sensing.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T10:04:30Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2009en
dc.identifier.doi10.14358/PERS.75.5.577en_US
dc.identifier.issn0099-1112
dc.identifier.urihttp://hdl.handle.net/11693/22768
dc.language.isoEnglishen_US
dc.publisherAmerican Society for Photogrammetry and Remote Sensingen_US
dc.relation.isversionofhttps://doi.org/10.14358/PERS.75.5.577en_US
dc.source.titlePhotogrammetric Engineering and Remote Sensingen_US
dc.subjectComparative experimentsen_US
dc.subjectData layeren_US
dc.subjectData sourceen_US
dc.subjectDecision tree classifiersen_US
dc.subjectFeature selectionen_US
dc.subjectLand cover classificationen_US
dc.subjectMissing dataen_US
dc.subjectMulti-sensor fusionen_US
dc.subjectMulti-sensor information fusionen_US
dc.subjectPerformance evaluationen_US
dc.subjectRemotely sensed imageryen_US
dc.subjectUnderstandabilityen_US
dc.subjectClassifiersen_US
dc.subjectData handlingen_US
dc.subjectDecision treesen_US
dc.subjectFeature extractionen_US
dc.subjectInformation fusionen_US
dc.subjectLearning systemsen_US
dc.subjectRemote sensingen_US
dc.subjectSensor data fusionen_US
dc.subjectComparative studyen_US
dc.subjectImage classificationen_US
dc.subjectLand coveren_US
dc.subjectModelingen_US
dc.subjectSensoren_US
dc.titleLand cover classification with multi-sensor fusion of partly missing dataen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Land_Cover_Classification_with_Multi_Sensor.pdf
Size:
6.22 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Scholarly Publications - Computer Engineering