Motion and Structure Estimation Using Fusion of Inertial and Vision Data for Helmet Tracker

Abstract

For weapon cueing and Head-Mounted Display (HMD), it is essentialto continuously estimate the motion of the helmet. The problem ofestimating and predicting the position and orientation of the helmetis approached by fusing measurements from inertial sensors and stereovision system. The sensor fusion approach in this paper is basedon nonlinear filtering, especially expended Kalman filter(EKF). Toreduce the computation time and improve the performance in visionprocessing, we separate the structure estimation and motion estimation.The structure estimation tracks the features which are the part ofhelmet model structure in the scene and the motion estimation filterestimates the position and orientation of the helmet. This algorithmis tested with using synthetic and real data. And the results showthat the result of sensor fusion is successful.