loading...
Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets
Ottawa, Ontario, Canada June 13-June 16
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/3DIM.2005.81Fifth International Conference on 3-D ...
 This Article 
 
Buy PURCHASE ARTICLE: $19
PDF
HTML
Buy IEEE Xplore Subscribers
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
ASCII Text
x 
 
M. Brown, D. G. Lowe, "Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets," 3D Digital Imaging and Modeling, International Conference on, pp. 56-63, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05), 2005.
 
 
BibTex
x
 
@article{ 10.1109/3DIM.2005.81,
author = {M. Brown and D. G. Lowe},
title = {Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets},
journal ={3D Digital Imaging and Modeling, International Conference on},
volume = {0},
year = {2005},
issn = {1550-6185},
pages = {56-63},
doi = {http://doi.ieeecomputersociety.org/10.1109/3DIM.2005.81},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - 3D Digital Imaging and Modeling, International Conference on
TI - Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets
SN - 1550-6185
SP56
EP63
A1 - M. Brown,
A1 - D. G. Lowe,
PY - 2005
KW - null
VL - 0
JA - 3D Digital Imaging and Modeling, International Conference on
ER -
 
M. Brown, University of British Columbia
D. G. Lowe, University of British Columbia
This paper presents a system for fully automatic recognition and reconstruction of 3D objects in image databases. We pose the object recognition problem as one of finding consistent matches between all images, subject to the constraint that the images were taken from a perspective camera. We assume that the objects or scenes are rigid. For each image we associate a camera matrix, which is parameterised by rotation, translation and focal length. We use invariant local features to find matches between all images, and the RANSAC algorithm to find those that are consistent with the fundamental matrix. Objects are recognised as subsets of matching images. We then solve for the structure and motion of each object, using a sparse bundle adjustment algorithm. Our results demonstrate that it is possible to recognise and reconstruct 3D objects from an unordered image database with no user input at all.
Citation:
M. Brown, D. G. Lowe, "Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets," 3dim, pp.56-63, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05), 2005
Usage of this product signifies your acceptance of the Terms of Use.