Low-Cost Augmented Reality Systems via 3D Point Cloud Sensors

In this paper, we explore the use of widely available and low-priced 3D point cloud sensors, such as the Microsoft XBox Kinect and Asus Xtion PRO LIVE, in the application of computer-generated imagery in live-video streams in Augmented Reality (AR) systems. Specifically, we examine the typical pipeline of AR applications and explore the potential simplifications derived from the use of such devices during the calibration and registration steps, which are the most computationally expensive and time consuming. Moreover, we describe how to approach the problem of face alignment, that is the aligning of a previously captured model of a face to newly captured data, by using 3D point cloud data and open-source libraries.