Pose Tracking Using Motion State Estimation for Mobile Augmented Reality

We present an efficient pose tracking method for mobile augmented reality. Although the conventional pyramid-based coarse-to-fine approach has good precision and robustness, it is too complex for low-spec mobile devices and speeding up pose tracking is essential. The proposed method focuses on the rapidity and linearity of the movement between successive frames, and omits unnecessary processing such as coarse tracking in a stable scene by performing motion state estimation (MSE) and switching the tracking algorithm accordingly. Experimental results demonstrate that our method is consistently faster than conventional pose tracking by nearly fifty percent, without any loss of precision or robustness by selecting the most appropriate tracking algorithm for a range of test sequences.