Visual Odometry from Two Point Correspondences and Initial Automatic Tilt Calibration
Wadenbäck, Mårten LU ; Karlsson, Martin LU ; Heyden, Anders LU
; Robertsson, Anders
LU
and Johansson, Rolf
LU
(2017)
12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017)
6.
p.340-346
- Abstract
- Ego-motion estimation is an important step towards fully autonomous mobile robots. In this paper we propose the use of an initial but automatic camera tilt calibration, which transforms the subsequent motion estimation to a 2D rigid body motion problem. This transformed problem is solved 2-optimally using RANSAC and a two-point method for rigid body motion. The method is experimentally evaluated using a camera mounted onto a mobile platform. The results are compared to measurements from a highly accurate external camera positioning system which are used as gold standard. The experiments show promising results on real data. © 2017 by SCITEPRESS - Science and Technology Publications, Lda.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/2491a5f4-e9eb-4834-b001-078cf51d8a10
- author
- Wadenbäck, Mårten
LU
; Karlsson, Martin
LU
; Heyden, Anders
LU
; Robertsson, Anders
LU
and Johansson, Rolf
LU
- organization
- publishing date
- 2017
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Visual Odometry, Tilted Camera, Trajectory Recovery
- host publication
- 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017)
- editor
- Imai, Francisco ; Tremeau, Alain and Braz, José
- volume
- 6
- pages
- 7 pages
- publisher
- SciTePress
- conference name
- 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017)
- conference location
- Porto, Portugal
- conference dates
- 2017-02-27 - 2017-03-01
- external identifiers
-
- scopus:85047851712
- DOI
- 10.5220/0006079903400346
- project
- ENGROSS
- RobotLab LTH
- language
- English
- LU publication?
- yes
- additional info
- The paper was presented at the 12th International Conference on Computer Vision Theory and Applications (VISAPP 2017), which formed a part of VISIGRAPP 2017. The conference website can be found at: www.visapp.visigrapp.org/?y=2017
- id
- 2491a5f4-e9eb-4834-b001-078cf51d8a10
- date added to LUP
- 2017-06-09 14:49:55
- date last changed
- 2024-04-14 12:17:11
@inproceedings{2491a5f4-e9eb-4834-b001-078cf51d8a10,
abstract = {{Ego-motion estimation is an important step towards fully autonomous mobile robots. In this paper we propose the use of an initial but automatic camera tilt calibration, which transforms the subsequent motion estimation to a 2D rigid body motion problem. This transformed problem is solved 2-optimally using RANSAC and a two-point method for rigid body motion. The method is experimentally evaluated using a camera mounted onto a mobile platform. The results are compared to measurements from a highly accurate external camera positioning system which are used as gold standard. The experiments show promising results on real data. © 2017 by SCITEPRESS - Science and Technology Publications, Lda.}},
author = {{Wadenbäck, Mårten and Karlsson, Martin and Heyden, Anders and Robertsson, Anders and Johansson, Rolf}},
booktitle = {{12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017)}},
editor = {{Imai, Francisco and Tremeau, Alain and Braz, José}},
keywords = {{Visual Odometry; Tilted Camera; Trajectory Recovery}},
language = {{eng}},
pages = {{340--346}},
publisher = {{SciTePress}},
title = {{Visual Odometry from Two Point Correspondences and Initial Automatic Tilt Calibration}},
url = {{https://lup.lub.lu.se/search/files/26947230/visual_odometry_visapp_2017.pdf}},
doi = {{10.5220/0006079903400346}},
volume = {{6}},
year = {{2017}},
}