Skip navigation
Skip navigation

A semi-supervised approach to space carving

Prakash, Surya; Robles-Kelly, Antonio

Description

In this paper, we present a semi-supervised approach to space carving by casting the recovery of volumetric data from multiple views into an evidence combining setting. The method presented here is statistical in nature and employs, as a starting point, a manually obtained contour. By making use of this user-provided information, we obtain probabilistic silhouettes of all successive images. These silhouettes provide a prior distribution that is then used to compute the probability of a voxel...[Show more]

dc.contributor.authorPrakash, Surya
dc.contributor.authorRobles-Kelly, Antonio
dc.date.accessioned2015-12-07T22:16:09Z
dc.identifier.issn0031-3203
dc.identifier.urihttp://hdl.handle.net/1885/17913
dc.description.abstractIn this paper, we present a semi-supervised approach to space carving by casting the recovery of volumetric data from multiple views into an evidence combining setting. The method presented here is statistical in nature and employs, as a starting point, a manually obtained contour. By making use of this user-provided information, we obtain probabilistic silhouettes of all successive images. These silhouettes provide a prior distribution that is then used to compute the probability of a voxel being carved. This evidence combining setting allows us to make use of background pixel information. As a result, our method combines the advantages of shape-from-silhouette techniques and statistical space carving approaches. For the carving process, we propose a new voxelated space. The proposed space is a projective one that provides a colour mapping for the object voxels which is consistent in terms of pixel coverage with their projection onto the image planes for the imagery under consideration. We provide quantitative results and illustrate the utility of the method on real-world imagery.
dc.publisherPergamon-Elsevier Ltd
dc.sourcePattern Recognition
dc.subjectKeywords: 3D reconstruction; Background pixels; Colour mapping; Image plane; Multiple views; Prior distribution; Quantitative result; Real-world; Semi-supervised; Semi-supervised methods; Shape-from-silhouette; Space carving; Space carvings; Volumetric data; Volume 3D reconstruction; Semi-supervised methods; Space carving; Volumetric reconstruction
dc.titleA semi-supervised approach to space carving
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume43
dc.date.issued2010
local.identifier.absfor080109 - Pattern Recognition and Data Mining
local.identifier.ariespublicationf2965xPUB3
local.type.statusPublished Version
local.contributor.affiliationPrakash, Surya, College of Engineering and Computer Science, ANU
local.contributor.affiliationRobles-Kelly, Antonio, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.issue2
local.bibliographicCitation.startpage506
local.bibliographicCitation.lastpage518
local.identifier.doi10.1016/j.patcog.2009.03.026
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2016-02-24T08:27:05Z
local.identifier.scopusID2-s2.0-70349443426
local.identifier.thomsonID000271145000009
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Prakash_A_semi-supervised_approach_to_2010.pdf761.18 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator