A modern tool being explored by researchers is the technological augmentation of human perception known as Augmented Reality (AR). In this paradigm the user sees the real world along with virtual objects and annotations of that world. This synthesis requires the proper registration of virtual information with the real scene, implying the computer's knowledge of the user's viewpoint. Current computer vision techniques, using planar targets within a captured video representation of the user's perspective, can be used to extract the mathematical definition of that perspective in real-time. These embedded targets can be subject to physical occlusion, which can corrupt the integrity of the calculations. This paper presents an occlusion silhouette extraction scheme that uses image stabilization to simplify the detection of target occlusion. Using this extraction scheme, the paper also presents a novel approach to hand gesture-based interaction with the virtual augmentation. An implemented interaction system is described, which applies this technology to the manipulation of a virtual control panel using simple hand gestures to simulate mouse control.
The 16th International Conference on Vision Interface [Proceedings].