Advanced

A Step Towards Self-calibration in SLAM: Weakly Calibrated On-line Structure and Motion Estimation

Haner, Sebastian LU and Heyden, Anders LU (2010) IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 In Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on p.59-64
Abstract
We propose a structure and motion estimation scheme based on a dynamic systems approach, where states and parameters in a perspective system are estimated. An online method for structure and motion estimation in densely sampled image sequences is presented. The proposed method is based on an extended Kalman filter and a novel parametrization. We derive a dynamic system describing the motion of the camera and the image formation. By a change of coordinates, we represent this system by normalized image coordinates and the inverse depths. Then we apply an extended Kalman filter for estimation of both structure and motion. Furthermore, we assume only weakly calibrated cameras, i.e. cameras with unknown and possibly varying focal length,... (More)
We propose a structure and motion estimation scheme based on a dynamic systems approach, where states and parameters in a perspective system are estimated. An online method for structure and motion estimation in densely sampled image sequences is presented. The proposed method is based on an extended Kalman filter and a novel parametrization. We derive a dynamic system describing the motion of the camera and the image formation. By a change of coordinates, we represent this system by normalized image coordinates and the inverse depths. Then we apply an extended Kalman filter for estimation of both structure and motion. Furthermore, we assume only weakly calibrated cameras, i.e. cameras with unknown and possibly varying focal length, unknown and constant principal point and known aspect ratio and skew. The performance of the proposed method is demonstrated in both simulated and real experiments. We also compare our method to the one proposed by Civera et al. and show that we get superior results. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on
pages
6 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010
external identifiers
  • scopus:77956496686
ISSN
2160-7516
2160-7508
ISBN
978-1-4244-7029-7 (Print)
DOI
10.1109/CVPRW.2010.5543256
language
English
LU publication?
yes
id
b515f0b5-0b4a-4f43-b1aa-f7f992afb516 (old id 4986115)
alternative location
http://www2.maths.lth.se/matematiklth/vision/publdb/reports/pdf/haner-heyden-iiwmv-10.pdf
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5543256
date added to LUP
2015-02-23 14:22:02
date last changed
2018-05-29 10:55:02
@inproceedings{b515f0b5-0b4a-4f43-b1aa-f7f992afb516,
  abstract     = {We propose a structure and motion estimation scheme based on a dynamic systems approach, where states and parameters in a perspective system are estimated. An online method for structure and motion estimation in densely sampled image sequences is presented. The proposed method is based on an extended Kalman filter and a novel parametrization. We derive a dynamic system describing the motion of the camera and the image formation. By a change of coordinates, we represent this system by normalized image coordinates and the inverse depths. Then we apply an extended Kalman filter for estimation of both structure and motion. Furthermore, we assume only weakly calibrated cameras, i.e. cameras with unknown and possibly varying focal length, unknown and constant principal point and known aspect ratio and skew. The performance of the proposed method is demonstrated in both simulated and real experiments. We also compare our method to the one proposed by Civera et al. and show that we get superior results.},
  author       = {Haner, Sebastian and Heyden, Anders},
  booktitle    = {Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on},
  isbn         = {978-1-4244-7029-7 (Print)},
  issn         = {2160-7516},
  language     = {eng},
  pages        = {59--64},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {A Step Towards Self-calibration in SLAM: Weakly Calibrated On-line Structure and Motion Estimation},
  url          = {http://dx.doi.org/10.1109/CVPRW.2010.5543256},
  year         = {2010},
}