A solution for multi-alignment by transformation synchronisation
(2015) IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 07-12-June-2015. p.2161-2169- Abstract
The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used. In practice the iterative methods perform well if the relative transformations between any pair of objects are free of noise. However, if only noisy relative transformations are available (e.g. due to missing data or wrong correspondences) the iterative methods may fail. Based on the observation that the underlying noise-free transformations can be retrieved from the null space of a matrix that can directly be obtained from pairwise alignments, this paper presents a novel method for the... (More)
The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used. In practice the iterative methods perform well if the relative transformations between any pair of objects are free of noise. However, if only noisy relative transformations are available (e.g. due to missing data or wrong correspondences) the iterative methods may fail. Based on the observation that the underlying noise-free transformations can be retrieved from the null space of a matrix that can directly be obtained from pairwise alignments, this paper presents a novel method for the synchronisation of pairwise transformations such that they are transitively consistent. Simulations demonstrate that for noisy transformations, a large proportion of missing data and even for wrong correspondence assignments the method delivers encouraging results.
(Less)
- author
- Bernard, Florian ; Thunberg, Johan LU ; Gemmar, Peter ; Hertel, Frank ; Husch, Andreas and Goncalves, Jorge
- publishing date
- 2015-10-14
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
- series title
- Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- volume
- 07-12-June-2015
- article number
- 7298828
- pages
- 9 pages
- publisher
- IEEE Computer Society
- conference name
- IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
- conference location
- Boston, United States
- conference dates
- 2015-06-07 - 2015-06-12
- external identifiers
-
- scopus:84959254736
- ISSN
- 1063-6919
- ISBN
- 9781467369640
- DOI
- 10.1109/CVPR.2015.7298828
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2015 IEEE.
- id
- d6ffe668-1824-476a-b9b2-7d6607b0b131
- date added to LUP
- 2024-09-05 12:34:15
- date last changed
- 2024-09-23 12:09:06
@inproceedings{d6ffe668-1824-476a-b9b2-7d6607b0b131,
abstract = {{<p>The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used. In practice the iterative methods perform well if the relative transformations between any pair of objects are free of noise. However, if only noisy relative transformations are available (e.g. due to missing data or wrong correspondences) the iterative methods may fail. Based on the observation that the underlying noise-free transformations can be retrieved from the null space of a matrix that can directly be obtained from pairwise alignments, this paper presents a novel method for the synchronisation of pairwise transformations such that they are transitively consistent. Simulations demonstrate that for noisy transformations, a large proportion of missing data and even for wrong correspondence assignments the method delivers encouraging results.</p>}},
author = {{Bernard, Florian and Thunberg, Johan and Gemmar, Peter and Hertel, Frank and Husch, Andreas and Goncalves, Jorge}},
booktitle = {{IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015}},
isbn = {{9781467369640}},
issn = {{1063-6919}},
language = {{eng}},
month = {{10}},
pages = {{2161--2169}},
publisher = {{IEEE Computer Society}},
series = {{Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}},
title = {{A solution for multi-alignment by transformation synchronisation}},
url = {{http://dx.doi.org/10.1109/CVPR.2015.7298828}},
doi = {{10.1109/CVPR.2015.7298828}},
volume = {{07-12-June-2015}},
year = {{2015}},
}