Browse by author
Lookup NU author(s): Dr Maryam HaroutunianORCiD, Dr Alan J Murphy, Professor Jeffrey Neasham, Dr Rosemary NormanORCiD
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND).
The application of visual odometry (VO) in mobile robotics and drones has become popular recently. However in the area of underwater unmanned vehicles, the VO method is yet to be applied widely because the density of feature points and illumination conditions are uncertain in underwater environments. Meanwhile, significant electronmagnetic wave attenuation in water means that underwater navigation remains a challenging problem. In this paper, a novel Integrated Visual Odometry system with a Stereo camera (IVO-S) has been investigated. Unlike pure visual odometry, such a method fuses the information from inertial sensors and a sonar so that it is able to work well in a context-sparse environment. In practical experiments, the vehicle was operated to follow specific closed-loop shapes, and an Intel T265 Tracking Camera with V-SLAM algorithm was used to provide comparative results. The cumulative error ratio is used as the quantitative evaluation method to analyze these practical test results. It is shown that the IVO method is a highly accurate navigation method, which can work in sparse environments, whilst also being a low cost solution.
Author(s): Xu Z, Haroutunian M, Murphy AJ, Neasham J, Norman R
Publication type: Article
Publication status: Published
Journal: Ocean Engineering
Year: 2020
Volume: 215
Print publication date: 01/11/2020
Online publication date: 26/08/2020
Acceptance date: 19/07/2020
Date deposited: 27/07/2020
ISSN (print): 0029-8018
ISSN (electronic): 1873-5258
Publisher: Elsevier
URL: https://doi.org/10.1016/j.oceaneng.2020.107822
DOI: 10.1016/j.oceaneng.2020.107822
Altmetrics provided by Altmetric