Utilizing sensor fusion in markerless mobile augmented reality

Čopič Pucihar, Klen and Coulton, Paul and Hutchinson, Daniel (2011) Utilizing sensor fusion in markerless mobile augmented reality. In: MobileHCI '11 Proceedings of the 13th International Conference on Human Computer Interaction with Mobile Devices and Services. ACM, New York. ISBN 9781450305419

Preview

PDF (AR Poster from Mobile HCI) - Submitted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1338Kb) | Preview

Abstract

One of the key challenges of markerless Augmented Reality (AR) systems, where no a priori information of the environment is available, is map and scale initialization. In such systems, the scale is unknown as it is impossible to determine the scale from a sequence of images alone. Implementing scale is vital for ensuring that augmented objects are contextually sensitive to the environment they are projected upon. In this paper we demonstrate a sensor and vision fusion approach for robust and user-friendly initialization of map and scale. The map is initialized, using inbuilt accelerometers, whilst scale is initialized by the camera auto-focusing capability. The later is possible by applying the Depth From Focus (DFF) method, which was, till now, limited to high precision camera systems. The demonstrated illustrates benefits of such a system, which is running on a commercially available mobile phone Nokia N900.

Actions (login required)