Persistent Link:
http://hdl.handle.net/10150/194661
Title:
Learning 3-D Models of Object Structure from Images
Author:
Schlecht, Joseph
Issue Date:
2010
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
Recognizing objects in images is an effortless task for most people.Automating this task with computers, however, presents a difficult challengeattributable to large variations in object appearance, shape, and pose. The problemis further compounded by ambiguity from projecting 3-D objects into a 2-D image.In this thesis we present an approach to resolve these issues by modeling objectstructure with a collection of connected 3-D geometric primitives and a separatemodel for the camera. From sets of images we simultaneously learn a generative,statistical model for the object representation and parameters of the imagingsystem. By learning 3-D structure models we are going beyond recognitiontowards quantifying object shape and understanding its variation.We explore our approach in the context of microscopic images of biologicalstructure and single view images of man-made objects composed of block-likeparts, such as furniture. We express detected features from both domains asstatistically generated by an image likelihood conditioned on models for theobject structure and imaging system. Our representation of biological structurefocuses on Alternaria, a genus of fungus comprising ellipsoid and cylindershaped substructures. In the case of man-made furniture objects, we representstructure with spatially contiguous assemblages of blocks arbitrarilyconstructed according to a small set of design constraints.We learn the models with Bayesian statistical inference over structure andcamera parameters per image, and for man-made objects, across categories, suchas chairs. We develop a reversible-jump MCMC sampling algorithm to exploretopology hypotheses, and a hybrid of Metropolis-Hastings and stochastic dynamicsto search within topologies. Our results demonstrate that we can infer both 3-Dobject and camera parameters simultaneously from images, and that doing soimproves understanding of structure in images. We further show how 3-D structuremodels can be inferred from single view images, and that learned categoryparameters capture structure variation that is useful for recognition.
Type:
text; Electronic Dissertation
Keywords:
3-D Object recognition; Computer vision; Machine learning; MCMC sampling; Statistical inference
Degree Name:
Ph.D.
Degree Level:
doctoral
Degree Program:
Computer Science; Graduate College
Degree Grantor:
University of Arizona
Committee Chair:
Barnard, Kobus

Full metadata record

DC FieldValue Language
dc.language.isoENen_US
dc.titleLearning 3-D Models of Object Structure from Imagesen_US
dc.creatorSchlecht, Josephen_US
dc.contributor.authorSchlecht, Josephen_US
dc.date.issued2010en_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractRecognizing objects in images is an effortless task for most people.Automating this task with computers, however, presents a difficult challengeattributable to large variations in object appearance, shape, and pose. The problemis further compounded by ambiguity from projecting 3-D objects into a 2-D image.In this thesis we present an approach to resolve these issues by modeling objectstructure with a collection of connected 3-D geometric primitives and a separatemodel for the camera. From sets of images we simultaneously learn a generative,statistical model for the object representation and parameters of the imagingsystem. By learning 3-D structure models we are going beyond recognitiontowards quantifying object shape and understanding its variation.We explore our approach in the context of microscopic images of biologicalstructure and single view images of man-made objects composed of block-likeparts, such as furniture. We express detected features from both domains asstatistically generated by an image likelihood conditioned on models for theobject structure and imaging system. Our representation of biological structurefocuses on Alternaria, a genus of fungus comprising ellipsoid and cylindershaped substructures. In the case of man-made furniture objects, we representstructure with spatially contiguous assemblages of blocks arbitrarilyconstructed according to a small set of design constraints.We learn the models with Bayesian statistical inference over structure andcamera parameters per image, and for man-made objects, across categories, suchas chairs. We develop a reversible-jump MCMC sampling algorithm to exploretopology hypotheses, and a hybrid of Metropolis-Hastings and stochastic dynamicsto search within topologies. Our results demonstrate that we can infer both 3-Dobject and camera parameters simultaneously from images, and that doing soimproves understanding of structure in images. We further show how 3-D structuremodels can be inferred from single view images, and that learned categoryparameters capture structure variation that is useful for recognition.en_US
dc.typetexten_US
dc.typeElectronic Dissertationen_US
dc.subject3-D Object recognitionen_US
dc.subjectComputer visionen_US
dc.subjectMachine learningen_US
dc.subjectMCMC samplingen_US
dc.subjectStatistical inferenceen_US
thesis.degree.namePh.D.en_US
thesis.degree.leveldoctoralen_US
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.grantorUniversity of Arizonaen_US
dc.contributor.chairBarnard, Kobusen_US
dc.contributor.committeememberBarnard, Kobusen_US
dc.contributor.committeememberEfrat, Alonen_US
dc.contributor.committeememberMorrison, Claytonen_US
dc.contributor.committeememberFasel, Ianen_US
dc.identifier.proquest10816en_US
dc.identifier.oclc659753694en_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.