Advanced

Covariance Propagation and Next Best View Planning for 3D Reconstruction

Haner, Sebastian LU and Heyden, Anders LU (2012) 12th European Conference on Computer Vision (ECCV 2012) In Computer Vision – ECCV 2012 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part II (Lecture Notes in Computer Science 7573) 7573. p.545-556
Abstract
This paper examines the potential benefits of applying next best view planning to sequential 3D reconstruction from unordered image sequences. A standard sequential structure-and-motion pipeline is extended with active selection of the order in which cameras are resectioned. To this end, approximate covariance propagation is implemented throughout the system, providing running estimates of the uncertainties of the reconstruction, while also enhancing robustness and accuracy. Experiments show that the use of expensive global bundle adjustment can be reduced throughout the process, while the additional cost of propagation is essentially linear in the problem size.
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
in
Computer Vision – ECCV 2012 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part II (Lecture Notes in Computer Science 7573)
editor
Fitzgibbon, Andrew; Lazebnik, Svetlana; Perona, Pietro; Sato, Yoichi; Schmid, Cordelia; ; ; ; and
volume
7573
pages
12 pages
publisher
Springer
conference name
12th European Conference on Computer Vision (ECCV 2012)
external identifiers
  • scopus:84867865196
ISSN
1611-3349
0302-9743
ISBN
978-3-642-33709-3
978-3-642-33708-6 (Print)
DOI
10.1007/978-3-642-33709-3_39
language
English
LU publication?
yes
id
5c91f2f7-5c27-4f78-9056-d01fe601b9d2 (old id 4986135)
alternative location
http://link.springer.com/chapter/10.1007/978-3-642-33709-3_39
date added to LUP
2015-02-23 14:43:21
date last changed
2017-08-13 03:23:48
@inproceedings{5c91f2f7-5c27-4f78-9056-d01fe601b9d2,
  abstract     = {This paper examines the potential benefits of applying next best view planning to sequential 3D reconstruction from unordered image sequences. A standard sequential structure-and-motion pipeline is extended with active selection of the order in which cameras are resectioned. To this end, approximate covariance propagation is implemented throughout the system, providing running estimates of the uncertainties of the reconstruction, while also enhancing robustness and accuracy. Experiments show that the use of expensive global bundle adjustment can be reduced throughout the process, while the additional cost of propagation is essentially linear in the problem size.},
  author       = {Haner, Sebastian and Heyden, Anders},
  booktitle    = {Computer Vision – ECCV 2012 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part II (Lecture Notes in Computer Science 7573)},
  editor       = {Fitzgibbon, Andrew and Lazebnik, Svetlana and Perona, Pietro and Sato, Yoichi and Schmid, Cordelia},
  isbn         = {978-3-642-33709-3},
  issn         = {1611-3349},
  language     = {eng},
  pages        = {545--556},
  publisher    = {Springer},
  title        = {Covariance Propagation and Next Best View Planning for 3D Reconstruction},
  url          = {http://dx.doi.org/10.1007/978-3-642-33709-3_39},
  volume       = {7573},
  year         = {2012},
}