Deep Learning for Underwater Visual Odometry Estimation

• Type: Article in International Scientific Journal
• Date: 2020

Authors

Bernardo Teixeira (Author) Other; Hugo Silva (Author) Other; Aníbal Matos (Author) FEUP; Eduardo Pereira da Silva (Author) Other

Journal

Title: IEEE Access

Vol. 8

Pages: 44687-44701

ISSN: 2169-3536

Publisher: IEEE

Indexing

ISI Web of Knowledge - 22 Citations

Scopus - 24 Citations

Other information

Authenticus ID: P-00R-TCZ

DOI: 10.1109/access.2020.2978406

Abstract (EN): This paper addresses Visual Odometry (VO) estimation in challenging underwater scenarios. Robot visual-based navigation faces several additional difficulties in the underwater context, which severely hinder both its robustness and the possibility for persistent autonomy in underwater mobile robots using visual perception capabilities. In this work, some of the most renown VO and Visual Simultaneous Localization and Mapping (v-SLAM) frameworks are tested on underwater complex environments, assessing the extent to which they are able to perform accurately and reliably on robotic operational mission scenarios. The fundamental issue of precision, reliability and robustness to multiple different operational scenarios, coupled with the rise in predominance of Deep Learning architectures in several Computer Vision application domains, has prompted a great a volume of recent research concerning Deep Learning architectures tailored for visual odometry estimation. In this work, the performance and accuracy of Deep Learning methods on the underwater context is also benchmarked and compared to classical methods. Additionally, an extension of current work is proposed, in the form of a visual-inertial sensor fusion network aimed at correcting visual odometry estimate drift. Anchored on a inertial supervision learning scheme, our network managed to improve upon trajectory estimates, producing both metrically better estimates as well as more visually consistent trajectory shape mimicking.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15