Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

City-Scale Localization for Cameras with Known Vertical Direction

Svärm, Linus LU ; Enqvist, Olof LU ; Kahl, Fredrik LU and Oskarsson, Magnus LU orcid (2017) In IEEE Transactions on Pattern Analysis and Machine Intelligence 39(7). p.1455-1461
Abstract

We consider the problem of localizing a novel image in a large 3D model, given that the gravitational vector is known. In principle, this is just an instance of camera pose estimation, but the scale of the problem introduces some interesting challenges. Most importantly, it makes the correspondence problem very difficult so there will often be a significant number of outliers to handle. To tackle this problem, we use recent theoretical as well as technical advances. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate... (More)

We consider the problem of localizing a novel image in a large 3D model, given that the gravitational vector is known. In principle, this is just an instance of camera pose estimation, but the scale of the problem introduces some interesting challenges. Most importantly, it makes the correspondence problem very difficult so there will often be a significant number of outliers to handle. To tackle this problem, we use recent theoretical as well as technical advances. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite cases with more than 99% outlier correspondences in city-scale models with several millions of 3D points.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Localization,, Camera Pose, Position Retrieval
in
IEEE Transactions on Pattern Analysis and Machine Intelligence
volume
39
issue
7
article number
7534854
pages
8 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • scopus:85020387389
  • wos:000402744400014
  • pmid:27514034
ISSN
0162-8828
DOI
10.1109/TPAMI.2016.2598331
language
English
LU publication?
yes
id
13749ab8-b71b-4184-b1d7-c5fa5e3bd181
date added to LUP
2016-09-05 19:20:00
date last changed
2025-03-09 19:17:00
@article{13749ab8-b71b-4184-b1d7-c5fa5e3bd181,
  abstract     = {{<p>We consider the problem of localizing a novel image in a large 3D model, given that the gravitational vector is known. In principle, this is just an instance of camera pose estimation, but the scale of the problem introduces some interesting challenges. Most importantly, it makes the correspondence problem very difficult so there will often be a significant number of outliers to handle. To tackle this problem, we use recent theoretical as well as technical advances. Many modern cameras and phones have gravitational sensors that allow us to reduce the search space. Further, there are new techniques to efficiently and reliably deal with extreme rates of outliers. We extend these methods to camera pose estimation by using accurate approximations and fast polynomial solvers. Experimental results are given demonstrating that it is possible to reliably estimate the camera pose despite cases with more than 99% outlier correspondences in city-scale models with several millions of 3D points.</p>}},
  author       = {{Svärm, Linus and Enqvist, Olof and Kahl, Fredrik and Oskarsson, Magnus}},
  issn         = {{0162-8828}},
  keywords     = {{Localization,; Camera Pose; Position Retrieval}},
  language     = {{eng}},
  month        = {{07}},
  number       = {{7}},
  pages        = {{1455--1461}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Pattern Analysis and Machine Intelligence}},
  title        = {{City-Scale Localization for Cameras with Known Vertical Direction}},
  url          = {{http://dx.doi.org/10.1109/TPAMI.2016.2598331}},
  doi          = {{10.1109/TPAMI.2016.2598331}},
  volume       = {{39}},
  year         = {{2017}},
}