An Inertial, Magnetic and Vision Based Trusted Pose Estimation for AR and 3D Data Qualification on Long Urban Pedestrian Displacements

In the context of pedestrian navigation, urban environment constitutes a challenging area for both localization and Augmented Reality (AR). In order to display 3D Geographic Information System (GIS) content in AR and to qualify them, we propose to fuse the pose estimated using vision thanks to a precisely known 3D urban furniture model with rotation estimated from inertial and magnetic measurements. An acquisition conducted in urban environment on a long pedestrian path permits to validate the contribution of sensors fusion and allows to qualify the pose estimation needed for AR 3D GIS content characterization.