6D Visual Odometry with Dense Probabilistic Egomotion Estimation
Hugo Silva, Alexandre Bernardino, Eduardo Silva
2013
Abstract
We present a novel approach to 6D visual odometry for vehicles with calibrated stereo cameras. A dense probabilistic egomotion (5D) method is combined with robust stereo feature based approaches and Extended Kalman Filtering (EKF) techniques to provide high quality estimates of vehicle’s angular and linear velocities. Experimental results show that the proposed method compares favorably with state-the-art approaches, mainly in the estimation of the angular velocities, where significant improvements are achieved.
DownloadPaper Citation
in Harvard Style
Silva H., Bernardino A. and Silva E. (2013). 6D Visual Odometry with Dense Probabilistic Egomotion Estimation . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 361-365. DOI: 10.5220/0004196103610365
in Bibtex Style
@conference{visapp13,
author={Hugo Silva and Alexandre Bernardino and Eduardo Silva},
title={6D Visual Odometry with Dense Probabilistic Egomotion Estimation},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={361-365},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004196103610365},
isbn={978-989-8565-48-8},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - 6D Visual Odometry with Dense Probabilistic Egomotion Estimation
SN - 978-989-8565-48-8
AU - Silva H.
AU - Bernardino A.
AU - Silva E.
PY - 2013
SP - 361
EP - 365
DO - 10.5220/0004196103610365