Application and evaluation of direct sparse visual odometry in marine vessels

With the international community pushing for a computer vision based option to the laws requiring a look-out for marine vehicles, there is now a significant motivation to provide digital solutions for navigation using these envisioned mandatory visual sensors. This paper explores the monocular direct sparse odometry algorithm when applied to a typical marine environment. The method uses a single camera to estimate a vessel's motion and position over time and is then compared to ground truth to establish feasibility as both a local and global navigation system. Whilst it was inconsistent in accurately estimating vessel position, it was found that it could consistently estimate the vessel's orientation in the majority of the situations the vessel was tasked with. It is therefore shown that monocular direct sparse odometry is partially suitable as a standalone navigation system and is a strong base for a multi-sensor solution.