Virtual-real registration in Outdoor Augmented Reality is committed to enhance user's spatial cognition by overlaying
virtual geographical objects on real scene. According to analyze fiducial detection registration method in indoor AR, for
the purpose of avoiding complex and tedious process of position tracking and camera calibration in traditional
registration methods, it puts forward and practices a virtual-real spatial information visualization registration method
using affine representations. Based on the observation from Koenderink and van Doorn, Ullman and Basri in 1991 which
is given a set of four or more non-coplanar 3D points, the projection of all points in the set can be computed as a linear
combination of the projection of just four of the points, it sets up global affine coordinate system in light of world
coordinates, camera coordinates and virtual coordinates and extracts four feature points from scene image and calculates
the global affine coordinates of key points of virtual objects. Then according to a linear homogeneous coordinates of the
four feature point's projection, it calculates projection pixel coordinates of key points of virtual objects. In addition, it
proposes an approach to obtain pixel relative depth for hidden surface removal. Finally, by a case study, it verifies the
feasibility and efficiency of the registration methods. The method would not only explore a new research direction for
Geographical Information Science, but also would provide location-based information and services for outdoor AR.
|