Dynamic registration correction in video-based augmented reality systems

This paper addresses the problem of correcting visual registration errors in video-based augmented reality systems. Accurate visual registration between real and computergenerated objects in combined images is critically important for conveying the perception that both types of object occupy the same 3-dimensional (3D) space. Previous augmented reality systems concentrated on improving 3D coordinate system registration in order to reduce image registration error. This paper introduces the idea of dynamically measuring 2D registration error in combined images and using that information to correct 3D coordinate system registration error which in turn improves registration in the combined images. Registration can be made exact for one or more points in every combined image if a small video delay can be tolerated. Our experimental system achieves improved image registration, stability, and error tolerance from tracking system drift and jitter over current augmented reality systems. Computer-generated objects can be "nailed" to real-world reference points in every image the user sees with an easily-implemented algorithm. Dynamic error correction as demonstrated here will likely be a key component of future video-based augmented reality systems.