Direct Stereo Visual Odometry based on Lines

Thomas Holzmann, Friedrich Fraundorfer, Horst Bischof

2016

Abstract

We propose a novel stereo visual odometry approach, which is especially suited for poorly textured environments. We introduce a novel, fast line segment detector and matcher, which detects vertical lines supported by an IMU. The patches around lines are then used to directly estimate the pose of consecutive cameras by minimizing the photometric error. Our algorithm outperforms state-of-the-art approaches in challenging environments. Our implementation runs in real-time and is therefore well suited for various robotics and augmented reality applications.

Paper Citation

in Harvard Style

Holzmann T., Fraundorfer F. and Bischof H. (2016). Direct Stereo Visual Odometry based on Lines . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 474-485. DOI: 10.5220/0005715604740485

in Bibtex Style

@conference{visapp16,
author={Thomas Holzmann and Friedrich Fraundorfer and Horst Bischof},
title={Direct Stereo Visual Odometry based on Lines},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={474-485},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005715604740485},
isbn={978-989-758-175-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - Direct Stereo Visual Odometry based on Lines
SN - 978-989-758-175-5
AU - Holzmann T.
AU - Fraundorfer F.
AU - Bischof H.
PY - 2016
SP - 474
EP - 485
DO - 10.5220/0005715604740485