Markerless augmented reality using image mosaics

Augmented reality is a powerful tool for delivering spatially coherent information to a user moving in a known environment. Accurate and reliable pose estimation is the key to success. Many approaches track reference objects into the scene but as the environment grows larger more objects need to be tracked leading to computationally intensive methods. Instead, we propose a practical approach that is suitable for environment where big planar structures are present. All the objects laying on the structure are composed into a large reference object using image mosaicing techniques, so that the problem is reduced to that of finding the pose from a single plane. Experimental results show the effectiveness of this approach on two interesting case studies such as aeronautical servicing and cultural heritage.