Robust real-time 3D trajectory tracking algorithms for visual tracking using weak perspective projection
Wei Guan Yau, Li‐Chen Fu, Dih‐Young Liu · 2001
In this paper, motion estimation algorithms for the most general tracking situation are developed. The proposed motion estimation algorithms are used to predict the location of target and then to generate a feasible control input so as to keep the target stationary in the center of the image. The work differs from the previous algorithm of motion estimation in that it is capable of decoupling the estimation of motion from the estimation of structure. The weak perspective projection is used to solve this problem. The modified optical flow is first calculated and then fed to motion estimation algorithms so as to generate an appropriate camera motion that achieves tracking. The important contribution of this work is that simple, numerically stable, none computation intensive, and correspondence-free 3D motion estimation algorithms are derived. A visual tracking system can be easily implemented and run in real-time due to the simplicity of the proposed algorithms and thus increases their efficiency. The robustness and feasibility of the proposed algorithms has been validated by a number of experiments.