Sensor Fusion Based Head Pose Tracking for Flight Cockpit System

Flight cockpit head tracking system is an important impetus for head pose tracking in fields of virtual or augmented reality. This paper presents a novel approach to dynamically track pilot's head pose using sensor fusion. The proposed approach utilizes a sensor fusion framework, composed of extended Kalman filters (EKF) and fusion filters (FF), to fuse poses from an inside-out tracking (IOT) and an outside-in tracking (OIT), which have complementary attributes. We established an experimental setup to verify the proposed approach and the experimental results showed that our tracking scheme based on sensor fusion is capable of achieving higher accurate, smoother and more stable position and orientation as well as better robustness compared with single IOT or OIT.