Reconfigurable computing for augmented reality

Abstract

Augmented reality involves combining three-dimensional real and synthetic objects for real-time user interaction. We describe a framework for supporting augmented reality applications by appropriate hardware and software. The benefits of reconfigurable computing, which allows optimised video analysis and synthesis to adapt to environmental changes, are explained using this framework. Our approach is illustrated by video mixing, image extraction, and object tracking. Prototype designs have been implemented using an FPGA-based platform and run at full video frame rate for images up to size 640 by 980 pixels.