Layer extraction with a bayesian model of shapes

Simple item page
dc.contributor.authorTorr, P.
dc.contributor.authorDick, A.R.
dc.contributor.authorCipolla, R.
dc.contributor.conferenceEuropean Conference on Computer Vision (ECCV) (26 Jun 2000 - 1 Jul 2000 : Dublin)
dc.date.issued2000
dc.description.abstractThis paper describes an automatic 3D surface modelling system that extracts dense 3D surfaces from uncalibrated video sequences. In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. The new segmentation method differs from previous methods in that it uses a specific prior model for layer shape. A probabilistic hierarchical model of layer shape is constructed, which assigns a density function to the shape and spatial relationships between layers. This allows accurate and efficient algorithms to be used when finding the best segmentation. Here this framework is applied to architectural scenes, in which layers commonly correspond to windows or doors and hence belong to a tightly constrained family of shapes.
dc.description.statementofresponsibilityP. H. S. Torr, A. R. Dick and R. Cipolla
dc.identifier.citationLecture Notes in Artificial Intelligence, 2000, vol.1843, pp.273-289
dc.identifier.doi10.1007/3-540-45053-X_18
dc.identifier.isbn3540676864
dc.identifier.isbn9783540676867
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.orcidDick, A.R. [0000-0001-9049-7345]
dc.identifier.urihttp://hdl.handle.net/2440/117097
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofseriesLecture notes in computer science ; Vol. 1843
dc.rights© Springer-Verlag Berlin Heidelberg 2000
dc.source.urihttps://doi.org/10.1007/3-540-45053-x_18
dc.subjectStructure from motion; grouping and segmentation
dc.titleLayer extraction with a bayesian model of shapes
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications
Australian Institute for Machine Learning publications