Advanced

Optimal Correspondences from Pairwise Constraints

Enqvist, Olof LU ; Josephson, Klas LU and Kahl, Fredrik LU (2009) IEEE International Conference on Computer Vision (ICCV), 2009 In IEEE International Conference on Computer Vision p.1295-1302
Abstract
Correspondence problems are of great importance in computer vision. They appear as subtasks in many applications such as object recognition, merging partial 3D reconstructions and image alignment. Automatically matching features from appearance only is difficult and errors are frequent. Thus, it is necessary to use geometric consistency to remove incorrect correspondences. Typically heuristic methods like RANSAC or EM-like algorithms are used, but they risk getting trapped in local optima and are in no way guaranteed to find the best solution. This paper illustrates how pairwise constraints in combination with graph methods can be used to efficiently find optimal correspondences. These ideas are implemented on two basic geometric problems,... (More)
Correspondence problems are of great importance in computer vision. They appear as subtasks in many applications such as object recognition, merging partial 3D reconstructions and image alignment. Automatically matching features from appearance only is difficult and errors are frequent. Thus, it is necessary to use geometric consistency to remove incorrect correspondences. Typically heuristic methods like RANSAC or EM-like algorithms are used, but they risk getting trapped in local optima and are in no way guaranteed to find the best solution. This paper illustrates how pairwise constraints in combination with graph methods can be used to efficiently find optimal correspondences. These ideas are implemented on two basic geometric problems, 3D-3D registration and 2D-3D registration. The developed scheme can handle large rates of outliers and cope with multiple hypotheses. Despite the combinatorial explosion, the resulting algorithm which has been extensively evaluated on real data, yields competitive running times compared to state of the art (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Computer Vision, Geometry, Pairwise Constraints, Optimal
in
IEEE International Conference on Computer Vision
pages
8 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE International Conference on Computer Vision (ICCV), 2009
external identifiers
  • wos:000294955300167
  • scopus:77953183492
ISSN
1550-5499
ISBN
978-1-4244-4419-9
DOI
10.1109/ICCV.2009.5459319
language
English
LU publication?
yes
id
b5c1671e-ca08-4042-8390-74a832753454 (old id 1454017)
date added to LUP
2009-08-07 00:26:14
date last changed
2017-12-10 04:23:33
@inproceedings{b5c1671e-ca08-4042-8390-74a832753454,
  abstract     = {Correspondence problems are of great importance in computer vision. They appear as subtasks in many applications such as object recognition, merging partial 3D reconstructions and image alignment. Automatically matching features from appearance only is difficult and errors are frequent. Thus, it is necessary to use geometric consistency to remove incorrect correspondences. Typically heuristic methods like RANSAC or EM-like algorithms are used, but they risk getting trapped in local optima and are in no way guaranteed to find the best solution. This paper illustrates how pairwise constraints in combination with graph methods can be used to efficiently find optimal correspondences. These ideas are implemented on two basic geometric problems, 3D-3D registration and 2D-3D registration. The developed scheme can handle large rates of outliers and cope with multiple hypotheses. Despite the combinatorial explosion, the resulting algorithm which has been extensively evaluated on real data, yields competitive running times compared to state of the art},
  author       = {Enqvist, Olof and Josephson, Klas and Kahl, Fredrik},
  booktitle    = {IEEE International Conference on Computer Vision},
  isbn         = {978-1-4244-4419-9},
  issn         = {1550-5499},
  keyword      = {Computer Vision,Geometry,Pairwise Constraints,Optimal},
  language     = {eng},
  pages        = {1295--1302},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Optimal Correspondences from Pairwise Constraints},
  url          = {http://dx.doi.org/10.1109/ICCV.2009.5459319},
  year         = {2009},
}