 |
Tracking in prepared spaces |
|
|
Tracking in prepared spaces |
This project is working on finding the best fiducial for use in
an Augmented Reality program. A fiducial is a small image that a camera can find
and use to determine where it is in space and how it's oriented. We use a method
based on Discrete Cosine Transform (DCT) basis images to make any curve into a
series of waves and place them on a 2D image. The camera can pick up these
images and use them as fiducials. The DCT can make numerous fiducials and allows
the camera to identify which is which very quickly.
Fiducial images are a common method for supporting vision-based tracking in augmented reality systems. This project addresses the question: what is the best fiducial? A set of criteria that are desirable in an optically tracked fiducial are presented and a new fiducial image set is designed that meets these criteria. The images in this set utilize a square black-border pattern with a 15% border width and an interior image that supports orientation determination and unique identification. The interior image is constructed from orthogonal DCT basis images chosen to minimize the probability of misidentification and to be robust to noise and occlusion.
"What is the best fiducial?" Charles B. Owen, Fan Xiao, and Paul Middlin, in The First IEEE International Augmented Reality Toolkit Workshop, September 29, 2002, Darmstadt, Germany, 98-105.
