A natural feature-based 3d object tracking method for wearable augmented reality

Abstract

In this paper, we describe a novel natural feature based 3-D object tracking method. Our method determines geometric relation between known 3-D objects and a camera, not using fiducial markers. Since our method only uses a camera to determine this geometric relation, it is suitable for wearable augmented reality (AR) systems. Our method combines two different types of approaches for tracking: a bottom up approach (BUA) and a top down approach (TDA). We mainly use a BUA, because it acquires accurate results with small calculation cost. When BUA cannot output an accurate result, our method starts TDA to avoid mistracking. An experimental result shows an accuracy and integrity of our method.