Indoor Localisation and Navigation on Augmented Reality Devices

Abstract

We present a novel indoor mapping and localisation approach for Augmented Reality (AR) devices that exploits the fusion of inertial sensors with visual odometry. We have demonstrated the approach using Google Glass (GG) and Google Cardboard (GC) supported with an Android phone. Our work presents an application of Extended Kalman Filter (EKF) for sensor fusion for AR based application where previous work on Bag of Visual Words Pairs (BoVWP) [10] based image matching is used for bundle adjustment on Fused odometry. We present the empirical validation of this approach on three different indoor spaces in an office environment. We concluded that vision complimented with inertial data effectively compensate the ego-motion of the user, improving the accuracy of map generation and localisation.