Energy Minimisation by Concurrent Propagation with Applications to Stereo Matching

ResearchSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Gimel'farb, G en
dc.contributor.advisor Delmas, P en Gong, Rui en 2017-06-01T22:23:37Z en 2017 en
dc.identifier.uri en
dc.description.abstract Classical energy minimisation paradigm based on probabilistic models of input and output data, employs an energy functional which combines the weighted prior energy of output, with a conditional energy of the input given the output. The regularising weight controls an adequacy of solutions establishing the correspondence between input and output data, to select a unique goal solution out of a multiplicity of these solutions for most frequent ill-posed problems. Such a weight is usually chosen by hand, and different choices may affect the output in unpredictable ways. This thesis proposes an alternative Two-Stage energy minimisation paradigm by treating separately both the energy terms. The First-Stage employs a very simplistic prior to obtain and store a whole set of minimisers of the ill-posed and non- regularised initial problem. Then the second stage selects an adequate solution only within the stored set of minimisers. The proposed Two-Stage paradigm needs no regularising weight, which implicitly pursues two different goals: to choose a suitable solution amongst the set of energy minimisers and include to this set not only primary but also secondary minimisers of the unregularised energy to account for unavoidable random deviations (noise) of the input data. en
dc.publisher ResearchSpace@Auckland en
dc.relation.ispartof PhD Thesis - University of Auckland en
dc.relation.isreferencedby UoA99264922007702091 en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri en
dc.rights.uri en
dc.title Energy Minimisation by Concurrent Propagation with Applications to Stereo Matching en
dc.type Thesis en Computer Science en The University of Auckland en Doctoral en PhD en
dc.rights.holder Copyright: The author en
dc.rights.accessrights en
pubs.elements-id 628181 en
pubs.record-created-at-source-date 2017-06-02 en

Full text options

This item appears in the following Collection(s)

Show simple item record Except where otherwise noted, this item's license is described as


Search ResearchSpace

Advanced Search