AR Cultural Heritage Reconstruction Based on Feature Landmark Database Constructed by Using Omnidirectional Range Sensor

Abstract

This paper describes an application of augmented reality (AR) techniques to virtual cultural heritage reconstruction on the real sites of defunct constructs. To realize AR-based cultural heritage reconstruction, extrinsic camera parameter estimation is required for geometric registration of real and virtual worlds. To estimate extrinsic camera parameters, we use a pre-constructed feature landmark database of the target environment. Conventionally, a feature landmark database has been constructed in a large-scale environment using a structure -from-motion technique for omnidirectional image sequences. However, the accuracy of estimated camera parameters is insufficient for specific applications like AR-based cultural heritage reconstruction, which needs to overlay CG objects at the position close to the user's viewpoint. This is due to the difficulty in compensation of the appearance change of close landmarks only from the sparse 3-D information obtained by structure-from-motion. In this paper, visual patterns of landmarks are compensated for by considering local shapes obtained by omnidirectional range finder to find corresponding landmarks existing close to the user. By using these landmarks with local shapes, accurate geometric registration is achieved for AR sightseeing in historic sites.