Show simple item record

dc.contributor.authorTaati, Babak
dc.contributor.otherQueen's University (Kingston, Ont.). Theses (Queen's University (Kingston, Ont.))en
dc.date2009-09-01 11:07:32.084en
dc.date.accessioned2009-09-01T15:33:38Z
dc.date.available2009-09-01T15:33:38Z
dc.date.issued2009-09-01T15:33:38Z
dc.identifier.urihttp://hdl.handle.net/1974/5107
dc.descriptionThesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2009-09-01 11:07:32.084en
dc.description.abstractWe formulate Local Shape Descriptor selection for model-based object recognition in range data as an optimization problem and offer a platform that facilitates a solution. The goal of object recognition is to identify and localize objects of interest in an image. Recognition is often performed in three phases: point matching, where correspondences are established between points on the 3-D surfaces of the models and the range image; hypothesis generation, where rough alignments are found between the image and the visible models; and pose refinement, where the accuracy of the initial alignments is improved. The overall efficiency and reliability of a recognition system is highly influenced by the effectiveness of the point matching phase. Local Shape Descriptors are used for establishing point correspondences by way of encapsulating local shape, such that similarity between two descriptors indicates geometric similarity between their respective neighbourhoods. We present a generalized platform for constructing local shape descriptors that subsumes a large class of existing methods and allows for tuning descriptors to the geometry of specific models and to sensor characteristics. Our descriptors, termed as Variable-Dimensional Local Shape Descriptors, are constructed as multivariate observations of several local properties and are represented as histograms. The optimal set of properties, which maximizes the performance of a recognition system, depend on the geometry of the objects of interest and the noise characteristics of range image acquisition devices and is selected through pre-processing the models and sample training images. Experimental analysis confirms the superiority of optimized descriptors over generic ones in recognition tasks in LIDAR and dense stereo range images.en
dc.format.extent1318072 bytes
dc.format.mimetypeapplication/pdf
dc.languageenen
dc.language.isoenen
dc.relation.ispartofseriesCanadian thesesen
dc.rightsThis publication is made available by the authority of the copyright owner solely for the purpose of private study and research and may not be copied or reproduced except as permitted by the copyright laws without written authority from the copyright owner.en
dc.subjectComputer visionen
dc.subjectRange dataen
dc.subjectObject recognitionen
dc.subjectTrackingen
dc.subjectLocal shape descriptoren
dc.subjectPoint matchingen
dc.subjectPose estimationen
dc.subjectPose acquisitionen
dc.subject3-Den
dc.subject3Den
dc.subjectPoint clouden
dc.subjectSatellite trackingen
dc.subjectOptimizationen
dc.subjectRange image processingen
dc.subjectRange imageen
dc.subjectRANSACen
dc.subjectRegistrationen
dc.subjectAlignmenten
dc.subjectSurfaceen
dc.subjectComputational geometryen
dc.subjectDetectionen
dc.subjectLocalizationen
dc.subjectModel-baseden
dc.subjectObject identificationen
dc.subjectPoint correspondenceen
dc.subjectFeature selectionen
dc.subjectVariable-Dimensional Local Shape Descriptorsen
dc.subjectVD-LSDen
dc.subjectLSDen
dc.subjectGenetic algorithmen
dc.subjectSimulated annealingen
dc.subjectForward feature selectionen
dc.subjectMultivariate featuresen
dc.subjectSubset selectionen
dc.subjectLocal propertiesen
dc.subjectLIDARen
dc.subjectDense stereoen
dc.subjectStereoen
dc.subjectPrecisionen
dc.subjectFeature matchingen
dc.subjectMachine learningen
dc.subjectTrainingen
dc.subjectLearning phaseen
dc.subjectPreprocessingen
dc.titleGeneration and Optimization of Local Shape Descriptors for Point Matching in 3-D Surfacesen
dc.typethesisen
dc.description.degreePh.Den
dc.contributor.supervisorGreenspan, Michael A.en
dc.contributor.departmentElectrical and Computer Engineeringen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record