Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Image-based localization using hybrid feature correspondences

Josephson, Klas LU ; Byröd, Martin LU ; Kahl, Fredrik LU and Åström, Karl LU orcid (2007) IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007 p.2732-2739
Abstract
Where am I and what am I seeing? This is a classical vision problem and this paper presents a solution based on efficient use of a combination of 2D and 3D features. Given a model of a scene, the objective is to find the relative camera location of a new input image. Unlike traditional hypothesize-and-test methods that try to estimate the unknown camera position based on 3D model features only, or alternatively, based on 2D model features only, we show that using a mixture of such features, that is, a hybrid correspondence set, may improve performance. We use minimal cases of structure-from-motion for hypothesis generation in a RANSAC engine. For this purpose, several new and useful minimal cases are derived for calibrated, semi-calibrated... (More)
Where am I and what am I seeing? This is a classical vision problem and this paper presents a solution based on efficient use of a combination of 2D and 3D features. Given a model of a scene, the objective is to find the relative camera location of a new input image. Unlike traditional hypothesize-and-test methods that try to estimate the unknown camera position based on 3D model features only, or alternatively, based on 2D model features only, we show that using a mixture of such features, that is, a hybrid correspondence set, may improve performance. We use minimal cases of structure-from-motion for hypothesis generation in a RANSAC engine. For this purpose, several new and useful minimal cases are derived for calibrated, semi-calibrated and uncalibrated settings. Based on algebraic geometry methods, we show how these minimal hybrid cases can be solved efficiently. The whole approach has been validated on both synthetic and real data, and we demonstrate improvements compared to previous work. © 2007 IEEE. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Image-based localization, Hypothesize-and-test methods, Hypothesis generation
host publication
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
pages
2732 - 2739
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007
conference location
Minneapolis, MN, United States
conference dates
2007-06-17 - 2007-06-22
external identifiers
  • wos:000250382805043
  • other:CODEN: PIVRE9
  • scopus:34948900329
ISSN
1063-6919
DOI
10.1109/CVPR.2007.383353
language
English
LU publication?
yes
id
73f04202-43d5-4741-ab63-ee3ce6d32508 (old id 643530)
date added to LUP
2016-04-01 16:46:29
date last changed
2022-02-13 00:28:17
@inproceedings{73f04202-43d5-4741-ab63-ee3ce6d32508,
  abstract     = {{Where am I and what am I seeing? This is a classical vision problem and this paper presents a solution based on efficient use of a combination of 2D and 3D features. Given a model of a scene, the objective is to find the relative camera location of a new input image. Unlike traditional hypothesize-and-test methods that try to estimate the unknown camera position based on 3D model features only, or alternatively, based on 2D model features only, we show that using a mixture of such features, that is, a hybrid correspondence set, may improve performance. We use minimal cases of structure-from-motion for hypothesis generation in a RANSAC engine. For this purpose, several new and useful minimal cases are derived for calibrated, semi-calibrated and uncalibrated settings. Based on algebraic geometry methods, we show how these minimal hybrid cases can be solved efficiently. The whole approach has been validated on both synthetic and real data, and we demonstrate improvements compared to previous work. © 2007 IEEE.}},
  author       = {{Josephson, Klas and Byröd, Martin and Kahl, Fredrik and Åström, Karl}},
  booktitle    = {{Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}},
  issn         = {{1063-6919}},
  keywords     = {{Image-based localization; Hypothesize-and-test methods; Hypothesis generation}},
  language     = {{eng}},
  pages        = {{2732--2739}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Image-based localization using hybrid feature correspondences}},
  url          = {{https://lup.lub.lu.se/search/files/4776626/1245430.pdf}},
  doi          = {{10.1109/CVPR.2007.383353}},
  year         = {{2007}},
}