Models and methods for Bayesian object matching

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en Tamminen, Toni 2012-02-17T07:20:29Z 2012-02-17T07:20:29Z 2005-11-11
dc.identifier.isbn 951-22-7907-X
dc.identifier.issn 1457-1404
dc.description.abstract This thesis is concerned with a central aspect of computer vision, the object matching problem. In object matching the aim is to detect and precisely localize instances of a known object class in a novel image. Factors complicating the problem include the internal variability of object classes and external factors such as rotation, occlusion, and scale changes. In this thesis, the problem is approached from the feature-based point of view, in which objects are considered to consist of certain pertinent features, which are then located in the perceived image. The methodological framework applied in this thesis is probabilistic Bayesian inference. Bayesian inference is a branch of statistics which assigns a great role to the mathematical modeling of uncertainty. After describing the basics of Bayesian statistics the object matching problem problem is formulated as a Bayesian probability model and it is shown how certain necessary sampling algorithms can be applied to analyze the resulting probability distributions. The Bayesian approach to the problem partitions it naturally into two submodels; a feature appearance model and an object shape model. In this thesis, feature appearance is modeled statistically via a type of bandpass filters known as Gabor filters, whereas two different shape models are presented: a simpler hierarchical model with uncorrelated feature location variations, and a full covariance model containing the interdependeces of the features. Furthermore, a novel model for the dynamics of object shape changes is introduced. The most important contributions of this thesis are the proposed extensions to the basic matching model. It is demonstrated how it is very straightforward to adjust the Bayesian probability model when difficulties such as scale changes, occlusions and multiple object instances arise. The changes required to the sampling algorithms and their applicability to the changed conditions are also discussed. The matching performance of the proposed system is tested with different datasets, and capabilities of the extended model in adverse conditions are demonstrated. The results indicate that the proposed model is a viable alternative to object matching, with performance equal or superior to existing approaches. en
dc.format.extent 116
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher Helsinki University of Technology en
dc.publisher Teknillinen korkeakoulu fi
dc.relation.ispartofseries Helsinki University of Technology Laboratory of Computational Engineering publications. Report B en
dc.relation.ispartofseries 52 en
dc.subject.other Electrical engineering en
dc.subject.other Medical sciences en
dc.title Models and methods for Bayesian object matching en
dc.type G4 Monografiaväitöskirja fi
dc.description.version reviewed en
dc.contributor.department Department of Electrical and Communications Engineering en
dc.contributor.department Sähkö- ja tietoliikennetekniikan osasto fi
dc.subject.keyword statistical image analysis en
dc.subject.keyword object recognition en
dc.subject.keyword Monte Carlo simulation en
dc.subject.keyword Bayesian inference en
dc.identifier.urn urn:nbn:fi:tkk-005907
dc.type.dcmitype text en
dc.type.ontasot Väitöskirja (monografia) fi
dc.type.ontasot Doctoral dissertation (monograph) en
dc.contributor.lab Laboratory of Computational Engineering en
dc.contributor.lab Laskennallisen tekniikan laboratorio fi

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication


My Account