The Course Angle aided Gaussian Mixture PHD Fuzzy Filter

In multi-target tracking systems, the number of the targets is unknown or varied with time, In this paper, The course angle aided Gaussian mixture PHD filter is proposed according to the limitations of Gaussian mixture PHD filter in the non-linear Gaussian condition. Firstly, the method of making use of radar measurements to calculate course angle is proposed and the course angle is combined with range and azimuth as a composite measurement, the tracking precision of target position is improved; Then the measurements are used to generate the target-birth PHD, the estimated number of the targets is more accurate; In addition, the cubature Kalman filter (CKF) is introduced to calculate the prediction and update distributions of target states. Finally, fuzzy method is used to determine targets’ tracks. The simulation results demonstrate the state trajectorys are provided and the improved performance of the proposed algorithm at target position, velocity and number of the targets.