Radially distorted planar motion compatible homographies
(2020) 9th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2020 1. p.280-288- Abstract
Fast and accurate homography estimation is essential to many computer vision applications, including scene degenerate cases and planarity detection. Such cases arise naturally in man-made environments, and failure to handle them will result in poor positioning estimates. Most modern day consumer cameras are affected by some level of radial distortion, which must be compensated for in order to get accurate estimates. This often demands calibration procedures, with specific scene requirements, and off-line processing. In this paper a novel polynomial solver for radially distorted planar motion compatible homographies is presented. The proposed algorithm is fast and numerically stable, and is proven on both synthetic and real data to work... (More)
Fast and accurate homography estimation is essential to many computer vision applications, including scene degenerate cases and planarity detection. Such cases arise naturally in man-made environments, and failure to handle them will result in poor positioning estimates. Most modern day consumer cameras are affected by some level of radial distortion, which must be compensated for in order to get accurate estimates. This often demands calibration procedures, with specific scene requirements, and off-line processing. In this paper a novel polynomial solver for radially distorted planar motion compatible homographies is presented. The proposed algorithm is fast and numerically stable, and is proven on both synthetic and real data to work well inside a RANSAC loop.
(Less)
- author
- Örnhag, Marcus Valtonen LU
- organization
- publishing date
- 2020
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Homography, Planar Motion, Polynomial Solver, Radial Distortion, Trajectory Recovery, Visual Odometry
- host publication
- Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods : ICPRAM 2020 - ICPRAM 2020
- editor
- De Marsico, Maria ; di Baja, Gabriella Sanniti and Fred, Ana
- volume
- 1
- pages
- 9 pages
- publisher
- SciTePress
- conference name
- 9th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2020
- conference location
- Valletta, Malta
- conference dates
- 2020-02-22 - 2020-02-24
- external identifiers
-
- scopus:85082983852
- ISBN
- 9789897583971
- DOI
- 10.5220/0008893802800288
- language
- English
- LU publication?
- yes
- id
- d67e2ca1-8396-46fd-9786-dead8c5fe33d
- date added to LUP
- 2020-05-27 14:08:22
- date last changed
- 2022-05-04 17:58:41
@inproceedings{d67e2ca1-8396-46fd-9786-dead8c5fe33d, abstract = {{<p>Fast and accurate homography estimation is essential to many computer vision applications, including scene degenerate cases and planarity detection. Such cases arise naturally in man-made environments, and failure to handle them will result in poor positioning estimates. Most modern day consumer cameras are affected by some level of radial distortion, which must be compensated for in order to get accurate estimates. This often demands calibration procedures, with specific scene requirements, and off-line processing. In this paper a novel polynomial solver for radially distorted planar motion compatible homographies is presented. The proposed algorithm is fast and numerically stable, and is proven on both synthetic and real data to work well inside a RANSAC loop.</p>}}, author = {{Örnhag, Marcus Valtonen}}, booktitle = {{Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods : ICPRAM 2020}}, editor = {{De Marsico, Maria and di Baja, Gabriella Sanniti and Fred, Ana}}, isbn = {{9789897583971}}, keywords = {{Homography; Planar Motion; Polynomial Solver; Radial Distortion; Trajectory Recovery; Visual Odometry}}, language = {{eng}}, pages = {{280--288}}, publisher = {{SciTePress}}, title = {{Radially distorted planar motion compatible homographies}}, url = {{http://dx.doi.org/10.5220/0008893802800288}}, doi = {{10.5220/0008893802800288}}, volume = {{1}}, year = {{2020}}, }