Rectification from radially-distorted scales
(2018) 14th Asian Conference on Computer Vision (ACCV 2018) In Lecture notes in computer science (LNCS) 11365. p.36-52- Abstract
- This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from repetitions of rigidly-transformed coplanar local features. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle images that contain nearly any type of coplanar repeated content. We demonstrate a principled approach to generating stable minimal solvers by the Gröbner basis method, which is accomplished by sampling feasible monomial bases to maximize numerical stability. Synthetic and real-image experiments confirm that the solvers give accurate rectifications from noisy measurements if used in a ransac-based estimator. The proposed solvers demonstrate superior... (More)
- This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from repetitions of rigidly-transformed coplanar local features. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle images that contain nearly any type of coplanar repeated content. We demonstrate a principled approach to generating stable minimal solvers by the Gröbner basis method, which is accomplished by sampling feasible monomial bases to maximize numerical stability. Synthetic and real-image experiments confirm that the solvers give accurate rectifications from noisy measurements if used in a ransac-based estimator. The proposed solvers demonstrate superior robustness to noise compared to the state of the art. The solvers work on scenes without straight lines and, in general, relax strong assumptions about scene content made by the state of the art. Accurate rectifications on imagery taken with narrow focal length to fisheye lenses demonstrate the wide applicability of the proposed method. The method is automatic, and the code is published at https://github.com/prittjam/repeats. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/e7625707-0e9c-43ed-8b0c-db8b5328dc40
- author
- Pritts, James ; Kukelova, Zuzana ; Larsson, Viktor LU and Chum, Ondřej
- organization
- publishing date
- 2018
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Rectification, Radial lens distortion, Repeated patterns
- host publication
- Computer Vision – ACCV 2018 : 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part V - 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part V
- series title
- Lecture notes in computer science (LNCS)
- volume
- 11365
- pages
- 17 pages
- publisher
- Springer
- conference name
- 14th Asian Conference on Computer Vision (ACCV 2018)
- conference location
- Perth, Australia
- conference dates
- 2018-12-02 - 2018-12-06
- external identifiers
-
- scopus:85066805073
- ISSN
- 1611-3349
- 0302-9743
- ISBN
- 978-3-030-20873-8
- 978-3-030-20872-1
- DOI
- 10.1007/978-3-030-20873-8_3
- language
- English
- LU publication?
- yes
- id
- e7625707-0e9c-43ed-8b0c-db8b5328dc40
- date added to LUP
- 2022-09-06 11:41:25
- date last changed
- 2024-03-06 12:59:59
@inproceedings{e7625707-0e9c-43ed-8b0c-db8b5328dc40,
abstract = {{This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from repetitions of rigidly-transformed coplanar local features. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle images that contain nearly any type of coplanar repeated content. We demonstrate a principled approach to generating stable minimal solvers by the Gröbner basis method, which is accomplished by sampling feasible monomial bases to maximize numerical stability. Synthetic and real-image experiments confirm that the solvers give accurate rectifications from noisy measurements if used in a ransac-based estimator. The proposed solvers demonstrate superior robustness to noise compared to the state of the art. The solvers work on scenes without straight lines and, in general, relax strong assumptions about scene content made by the state of the art. Accurate rectifications on imagery taken with narrow focal length to fisheye lenses demonstrate the wide applicability of the proposed method. The method is automatic, and the code is published at https://github.com/prittjam/repeats.}},
author = {{Pritts, James and Kukelova, Zuzana and Larsson, Viktor and Chum, Ondřej}},
booktitle = {{Computer Vision – ACCV 2018 : 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part V}},
isbn = {{978-3-030-20873-8}},
issn = {{1611-3349}},
keywords = {{Rectification; Radial lens distortion; Repeated patterns}},
language = {{eng}},
pages = {{36--52}},
publisher = {{Springer}},
series = {{Lecture notes in computer science (LNCS)}},
title = {{Rectification from radially-distorted scales}},
url = {{http://dx.doi.org/10.1007/978-3-030-20873-8_3}},
doi = {{10.1007/978-3-030-20873-8_3}},
volume = {{11365}},
year = {{2018}},
}