Camera Pose Estimation by Vision-inertial Sensor Fusion: An Application to Augmented Reality Books

Abstract

As the booming of mobile technologies, handheld Augmented Reality draws increasing attention. One crucial process is the position and orientation estimation of the handheld device relative to a reference coordinate system in order to display the virtual content accurately upon thereal world. An emerging application is to integrate multimedia elements (e.g., text, images, sound, video) in physical real books to enhance the learning process or provide amusement and interaction. Square markers are popularly used due to their ease-to-use and high accuracy. However, thesemarkers cause visual discomfort. This paper introduces a novel pose tracking approach for mobile devices by combining a tricolored strip, an internal camera and embedded inertial sensors. Furthermore, the application to books is studied. The proposed approach is less intrusive than squaremarkers due to its reduced size and provides accurate six-degree-of-freedom pose estimation in real time.

Publication
IS&T International Symposium on Electronic Imaging 2016