Markerless Indoor/Outdoor Augmented Reality Navigation Device Based on ORB-Visual-Odometry Positioning Estimation and Wall-Floor-Boundary Image Registration

Abstract

For markerless indoor/outdoor Augmented Reality Navigation (ARN) technology, camera pose is inevitably the fundamental argument of positioning estimation and pose estimation, and floor plane is indispensably the fiducial target of image registration. This paper proposes ORB-visual-odometry positioning estimation and wall-floor-boundary image registration to make ARN more precise, reliable, and instantaneous. Experimental results show both ORB-visual-odometry positioning estimation and wall-floor-boundary image registration have higher accuracy and less latency than conventional well-known positioning estimation and image registration methods for ARN. On the other hand, these proposed two methods are seamlessly implemented on the handheld Android embedded platform and are smoothly verified to work well on the handheld indoor/outdoor augmented reality navigation device.