Radially-Distorted Conjugate Translations
(2018) 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 p.1993-2001- Abstract
This paper introduces the first minimal solvers that jointly solve for affine-rectification and radial lens distortion from coplanar repeated patterns. Even with imagery from moderately distorted lenses, plane rectification using the pinhole camera model is inaccurate or invalid. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle imagery, which is now common from consumer cameras. The solvers are derived from constraints induced by the conjugate translations of an imaged scene plane, which are integrated with the division model for radial lens distortion. The hidden-variable trick with ideal saturation is used to reformulate the constraints so that the solvers generated... (More)
This paper introduces the first minimal solvers that jointly solve for affine-rectification and radial lens distortion from coplanar repeated patterns. Even with imagery from moderately distorted lenses, plane rectification using the pinhole camera model is inaccurate or invalid. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle imagery, which is now common from consumer cameras. The solvers are derived from constraints induced by the conjugate translations of an imaged scene plane, which are integrated with the division model for radial lens distortion. The hidden-variable trick with ideal saturation is used to reformulate the constraints so that the solvers generated by the Gröbner-basis method are stable, small and fast. Rectification and lens distortion are recovered from either one conjugately translated affine-covariant feature or two independently translated similarity-covariant features. The proposed solvers are used in a RANSAC-based estimator, which gives accurate rectifications after few iterations. The proposed solvers are evaluated against the state-of-the-art and demonstrate significantly better rectifcations on noisy measurements. Qualitative results on diverse imagery demonstrate high-accuracy undistortion and rectification.
(Less)
- author
- Pritts, James ; Kukelova, Zuzana ; Larsson, Viktor LU and Chum, Ondrej
- organization
- publishing date
- 2018-12-17
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
- article number
- 8578311
- pages
- 9 pages
- publisher
- IEEE Computer Society
- conference name
- 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
- conference location
- Salt Lake City, United States
- conference dates
- 2018-06-18 - 2018-06-22
- external identifiers
-
- scopus:85062875944
- ISBN
- 9781538664209
- DOI
- 10.1109/CVPR.2018.00213
- language
- English
- LU publication?
- yes
- id
- 15758c33-868e-45ba-9a8c-e69542c59f33
- date added to LUP
- 2019-04-01 09:42:35
- date last changed
- 2022-09-06 09:57:22
@inproceedings{15758c33-868e-45ba-9a8c-e69542c59f33,
abstract = {{<p>This paper introduces the first minimal solvers that jointly solve for affine-rectification and radial lens distortion from coplanar repeated patterns. Even with imagery from moderately distorted lenses, plane rectification using the pinhole camera model is inaccurate or invalid. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle imagery, which is now common from consumer cameras. The solvers are derived from constraints induced by the conjugate translations of an imaged scene plane, which are integrated with the division model for radial lens distortion. The hidden-variable trick with ideal saturation is used to reformulate the constraints so that the solvers generated by the Gröbner-basis method are stable, small and fast. Rectification and lens distortion are recovered from either one conjugately translated affine-covariant feature or two independently translated similarity-covariant features. The proposed solvers are used in a RANSAC-based estimator, which gives accurate rectifications after few iterations. The proposed solvers are evaluated against the state-of-the-art and demonstrate significantly better rectifcations on noisy measurements. Qualitative results on diverse imagery demonstrate high-accuracy undistortion and rectification.</p>}},
author = {{Pritts, James and Kukelova, Zuzana and Larsson, Viktor and Chum, Ondrej}},
booktitle = {{Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018}},
isbn = {{9781538664209}},
language = {{eng}},
month = {{12}},
pages = {{1993--2001}},
publisher = {{IEEE Computer Society}},
title = {{Radially-Distorted Conjugate Translations}},
url = {{http://dx.doi.org/10.1109/CVPR.2018.00213}},
doi = {{10.1109/CVPR.2018.00213}},
year = {{2018}},
}