Real-time camera tracking for Augmented Reality

Real-time camera tracking is a system to estimate camera motion in real-time only given a image sequence in markerless background. It can be used in augmented reality application in which CG objects are inserted into live action plates by real-time. Proposed system is based on parallel processing and composed of two parts, they are feature tracking part, camera motion estimation part. In the feature tracking part, KLT features tracker is performed based on multi-core multi-thread processing using 4 qaudro CPU, total 16 CPU. In camera motion estimation part, camera motion and 3D location of each features are estimated using EKF.