Image-Based In Situ Modeling for Augmented Reality Offices and Rooms: A Motion-Based General Purpose Augmented Reality (AR) System for Planar Piecewise Worlds

In this work, we propose a computer vision-based AR system oriented to non-expert users that allows to add 3D computer generated (CG) objects into real man-made environments. Our system goes to a very intuitive and easy in situ 3D structure recovery of planar piecewise scenes without using powerful hardware nor commodity sensors. The user simply has to move the camera (translation of the focus is mandatory) and take two different pictures of the scene and our approach obtains a rough polyhedral representation of the environment suitable to conduct planar tracking for model-based augmented reality and to augment it with virtual objects coherently. Polyhedral representations of scenes are very convenient for offices and large rooms, hence we focus the potential applications of our system to augment offices and classrooms with virtual imagery.