Designing a vision-based collaborative augmented reality application from industrial training

摘要

Augmented reality is a variation of virtual reality. It allows the user to see computer generated virtual objects superimposed upon the real world through the use of some kind of see-through head-mounted display. Human users of such system can interact with the virtual world and have additional information, such as character description of physical objects and instruction for performing physical tasks in form of annotation, speech instruction, image, and 3D model. In this paper, we describe a prototype of a collaborative industrial teletraining system, based on distributed augmented reality. Distribution enables users on remote sites to collaborate on the training tasks by sharing the view of the local user equipped with a wearable computer. The users can interactively manipulate virtual objects that substitute for real objects, try out and discuss the training tasks. A new technique for identifying real world objects and estimating their coordinate systems is introduced. The method utilizes a Binary Square Marker, which can identify a great number of real world objects with markers tagged on them by using computer vision techniques.