부산대학교 도서관

Wearable inertial tracking is well accepted due to its convenience for free-style motion tracking with high accuracy. Traditionally, complicated high-order calculations for human kinematic modeling and inaccurate estimation of sensor placement are interfering the efficiency of real-time tracking. In order to tackle the challenges, a wearable human motion tracking system is developed by applying twists and exponential maps techniques. When the body segments are articulated by product of exponential maps, joint positions are continuously updated based on these techniques and their rotational angles are represented individually within the global frame. It is more efficient to achieve real-time motion tracking with low-order calculations. Meanwhile by applying the well-designed calibration procedure, it is more convenient to estimate a sensor's position and orientation regardless of knowing its placement. This paper presents our approach and exemplifies the assessment of proposed motion tracking system by several tests of limb and full body motion tracking. The comparisons with Vicon and OptiTrack motion capture systems verify satisfactorily high accuracy.