Multiple Object Tracking in Unprepared Environments Using Combined Feature for Augmented Reality Applications

Existing augmented reality (AR) applications performs well in tracking objects in prepared environments. However, tracking multiple objects in unprepared environments involves considerable difficulty to achieve best results since users are not allowed to modify the real environment such as in outdoor applications. This research focuses on a multiple object tracking based on combined feature tracking and color tracking in an arbitrary scene to demonstrate superior performance. This approach is beneficial to tracking technologies since additional visual cues provide seamless real-synthetic world integration. The system requires accurate measurements of the six-degree of freedom (6DOF) camera pose, three-degree of freedom (3DOF) for position and three for orientation relative to the world coordinate system. Our framework aims to lead AR applications in unprepared environments with multiple tracking objects regardless of the movement of real objects, lights and cameras.