Authors:
Thomas Belos
1
;
Pascal Monasse
1
and
Eva Dokladalova
2
Affiliations:
1
LIGM, Ecole des Ponts ParisTech, Université Gustave Eiffel, CNRS, F-77454 Marne-la-Vallée, France
;
2
LIGM, Université Gustave Eiffel, CNRS, ESIEE Paris, F-77454 Marne-la-Vallée, France
Keyword(s):
SLAM, Simultaneous Localizaton and Mapping, Odometry, Drift, Robust, Online, ORB, DSO, Photometric, Features, Indirect, Direct, Mixed, Hybrid.
Abstract:
In recent years, the state-of-the-art of monocular SLAM has seen remarkable advances in reducing errors and improving robustness. At the same time, this quality of results can be obtained in real-time on small CPUs. However, most algorithms have a high failure rate out-of-the-box. Systematic error such as drift remains still significant even for the best algorithms. This can be handled by a global measure as a loop closure, but it penalizes online data processing. We propose a mixed SLAM, based on ORB-SLAM2 and DSO: MOD SLAM. It is a fusion of photometric and feature-based methods, without being a simple copy of both. We propose a decision system to predict at each frame which optimization will produce the minimum drift so that only one will be selected to save computational time and resources. We propose a new implementation of the map that is equipped with the ability to actively work with DSO and ORB points at the same time. Our experimental results show that this method increases
the overall robustness and reduces the drift without compromising the computational resources. Contrary to the best state-of-the-art algorithms, MOD SLAM can handle 100% of KITTI, TUM, and random phone videos, without any configuration change.
(More)