FDMO: Feature Assisted Direct Monocular Odometry

Georges Younes, Daniel Asmar, John Zelek

2019

Abstract

Visual Odometry (VO) can be categorized as being either direct (e.g. DSO) or feature-based (e.g. ORB-SLAM). When the system is calibrated photometrically, and images are captured at high rates, direct methods have been shown to outperform feature-based ones in terms of accuracy and processing time; they are also more robust to failure in feature-deprived environments. On the downside, direct methods rely on heuristic motion models to seed an estimate of camera motion between frames; in the event that these models are violated (e.g., erratic motion), direct methods easily fail. This paper proposes FDMO (Feature assisted Direct Monocular Odometry), a system designed to complement the advantages of both direct and featured based techniques to achieve sub-pixel accuracy, robustness in feature deprived environments, resilience to erratic and large inter-frame motions, all while maintaining a low computational cost at frame-rate. Efficiencies are also introduced to decrease the computational complexity of the feature-based mapping part. FDMO shows an average of 10% reduction in alignment drift, and 12% reduction in rotation drift when compared to the best of both ORB-SLAM and DSO, while achieving significant drift (alignment, rotation & scale) reductions (51%, 61%, 7% respectively) going over the same sequences for a second loop. FDMO is further evaluated on the EuroC dataset and was found to inherit the resilience of feature-based methods to erratic motions, while maintaining the accuracy of direct methods.

Download


Paper Citation


in Harvard Style

Younes G., Asmar D. and Zelek J. (2019). FDMO: Feature Assisted Direct Monocular Odometry. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 737-747. DOI: 10.5220/0007524807370747


in Bibtex Style

@conference{visapp19,
author={Georges Younes and Daniel Asmar and John Zelek},
title={FDMO: Feature Assisted Direct Monocular Odometry},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={737-747},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007524807370747},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - FDMO: Feature Assisted Direct Monocular Odometry
SN - 978-989-758-354-4
AU - Younes G.
AU - Asmar D.
AU - Zelek J.
PY - 2019
SP - 737
EP - 747
DO - 10.5220/0007524807370747
PB - SciTePress