Uncalibrated Narrow Baseline Augmented RealityAnnie Yao, Andrew Calway, Uncalibrated Narrow Baseline Augmented Reality. 1st International Symposium on 3D Data Processing Visualization and Transmission. G. M Cortelazzo, C Guerra, (eds.). ISSN 0769515215, pp. 182–185. June 2002. PDF, 246 Kbytes.
We describe initial work on a system for augmenting video sequences with 3-D graphics so that they appear to be present within the scene. Our aim is to do this in real-time for sequences captured by uncalibrated `live' cameras, such as a hand-held or wearable. The paper focuses on obtaining 3-D camera motion and depth estimates for these types of sequences using sparse feature tracking and the recursive algorithm developed by Azarbayejani and Pentland. We report experiments which demonstrate that the approach performs well and discuss implementation issues relating to its use in a `live' real-time system.