Maneuvering target tracking and motion estimation using vision-aid particle filter
Fei Dong, Jiaqi Zhang, Keyou You · IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society · 2017
The purpose of this paper is to solve the problem of tracking a maneuvering ground moving target (GMT) in the presence of unknown control inputs by an unmanned aerial vehicle (UAV) equipped with a single vision camera. When the exact state information of the GMT is available, the efficiency of the Lyapunov guidance vector field approach has been proved. However, the case of unknown inputs and unavailable state information is still in suspense. By combining the guidance law with a vision-aid particle filter, we propose an integrated tracking algorithm. The guidance law could generate the desired velocity to direct the UAV to loiter around the GMT with a desired radius and airspeed, and the particle filter is capable to estimate the unknown inputs and further estimate the position and velocity of the GMT. The performance of the proposed tracking algorithm is demonstrated through computer simulations.