|Abstract:||Augmented Reality (AR) assisted navigation of marine vessels in port could lead to a reduction in accidents caused by human errors. To realize AR based ship navigation, it is necessary to accurately set the 3-dimensional spatial coordinates of the surroundings, to estimate the ship pose with high accuracy, and to present intuitive information based on them. In this paper, we propose an integration method of tracking information from Visual Simultaneous Localization and Mapping (VSLAM) / Global Navigation Satellite System (GNSS) / Inertial Navigation System using an Extended Kalman Filter. Our system does not require a network access, expensive Real-Time Kinematic or Precise Point Positioning. Our system is cost-effective as it utilizes only a monocular camera, plural single frequency GNSS cores, and a 6 Degree of Freedom Micro Electro Mechanical Systems Inertial Measurement Unit. To evaluate our system, we track the pose of a boat performing a berthing maneuver with our system using Accumulated Delta Range of GNSS carrier phase and with GNSS code-based positioning using Pseudo Range. Our results show that our system not only improves the scale estimation of the VSLAM system, but also the position accuracy of the ship from 0.66 m to 0.06 m on navigation coordinate. Finally, we present an intuitive AR interface that utilizes this information to support ship navigation.|
Proceedings of the 31st International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2018)
September 24 - 28, 2018
Hyatt Regency Miami
|Pages:||1765 - 1775|
|Cite this article:||
Nakamura, Hiraku, Sonobe, Tatsuya, Toda, Hiroyuki, Fujisawa, Naomi, Taketomi, Takafumi, Plopski, Alexander, Sandor, Christian, Kato, Hirokazu, "Fusion of VSLAM/GNSS/INS for Augmented Reality Navigation in Ports," Proceedings of the 31st International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2018), Miami, Florida, September 2018, pp. 1765-1775.
ION Members/Non-Members: 1 Download Credit