Abstract

3D registration of depth images has been studied extensively in the past. With emergence of low cost RGB-D cameras, many applications have emerged. Yet, the quality of alignment has much to improve. It remains a challenge to create a 3D model of the environment with high accuracy which could be used for engineering applications. Moreover, challenging scenarios where features are scarce, handling large areas as scene, enabling the user to freely roam around the scene for image acquisition in a practical manner, guiding the user in taking better images and accomplishing all of this with low cost RGB-D camera in real time is a subject which is yet to be improved. In this thesis, we address all this challenges by designing and implementing a mobile system that rely on markers. Our system detects and matches markers in real-time with very low CPU load. Moreover, this mobile 3D reconstruction system is interactive which enables a user not only to move freely while doing 3D reconstruction, but also makes the user aware of current status of 3D reconstruction in real-time.