Enforcing Image Consistency in Multiple 3-D Object Modelling

Matthew Grum; Adrian G. Bors

doi:10.1109/ICPR.2008.4760980

Enforcing Image Consistency in Multiple 3-D Object Modelling

Matthew Grum, Adrian G. Bors

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we present a new approach for modelling multiple object scenes using images taken from various viewpoints. The voxel representation produced by the space carving is used for estimating the parameters of radial basis function functions (RBFs). A new methodology is proposed for correcting the modelling errors within the RBF framework, by enforcing consistency with the input images by matching along epipolar lines, and enforcing silhouette constraints using the visual hull. The proposed methodology is applied on two datasets consisting of several objects while providing quantitative and qualitative assessment.

Original language	English
Title of host publication	19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6
Place of Publication	NEW YORK
Publisher	IEEE
Pages	132-135
Number of pages	4
ISBN (Print)	978-1-4244-2174-9
DOIs	https://doi.org/10.1109/ICPR.2008.4760980
Publication status	Published - 2008
Event	19th International Conference on Pattern Recognition (ICPR 2008) - Tampa Duration: 8 Dec 2008 → 11 Dec 2008

Conference

Conference	19th International Conference on Pattern Recognition (ICPR 2008)
City	Tampa
Period	8/12/08 → 11/12/08

Access to Document

10.1109/ICPR.2008.4760980

Cite this

@inproceedings{3e41e54afc564dc4a08324c536fbe8bf,

title = "Enforcing Image Consistency in Multiple 3-D Object Modelling",

abstract = "In this paper we present a new approach for modelling multiple object scenes using images taken from various viewpoints. The voxel representation produced by the space carving is used for estimating the parameters of radial basis function functions (RBFs). A new methodology is proposed for correcting the modelling errors within the RBF framework, by enforcing consistency with the input images by matching along epipolar lines, and enforcing silhouette constraints using the visual hull. The proposed methodology is applied on two datasets consisting of several objects while providing quantitative and qualitative assessment.",

author = "Matthew Grum and Bors, {Adrian G.}",

year = "2008",

doi = "10.1109/ICPR.2008.4760980",

language = "English",

isbn = "978-1-4244-2174-9",

pages = "132--135",

booktitle = "19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6",

publisher = "IEEE",

address = "United States",

note = "19th International Conference on Pattern Recognition (ICPR 2008) ; Conference date: 08-12-2008 Through 11-12-2008",

}

TY - GEN

T1 - Enforcing Image Consistency in Multiple 3-D Object Modelling

AU - Grum, Matthew

AU - Bors, Adrian G.

PY - 2008

Y1 - 2008

N2 - In this paper we present a new approach for modelling multiple object scenes using images taken from various viewpoints. The voxel representation produced by the space carving is used for estimating the parameters of radial basis function functions (RBFs). A new methodology is proposed for correcting the modelling errors within the RBF framework, by enforcing consistency with the input images by matching along epipolar lines, and enforcing silhouette constraints using the visual hull. The proposed methodology is applied on two datasets consisting of several objects while providing quantitative and qualitative assessment.

AB - In this paper we present a new approach for modelling multiple object scenes using images taken from various viewpoints. The voxel representation produced by the space carving is used for estimating the parameters of radial basis function functions (RBFs). A new methodology is proposed for correcting the modelling errors within the RBF framework, by enforcing consistency with the input images by matching along epipolar lines, and enforcing silhouette constraints using the visual hull. The proposed methodology is applied on two datasets consisting of several objects while providing quantitative and qualitative assessment.

UR - http://www.scopus.com/inward/record.url?scp=77957966296&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2008.4760980

DO - 10.1109/ICPR.2008.4760980

M3 - Conference contribution

SN - 978-1-4244-2174-9

SP - 132

EP - 135

BT - 19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6

PB - IEEE

CY - NEW YORK

T2 - 19th International Conference on Pattern Recognition (ICPR 2008)

Y2 - 8 December 2008 through 11 December 2008

ER -

Enforcing Image Consistency in Multiple 3-D Object Modelling

Abstract

Conference

Access to Document

Other files and links

Cite this