An Adaptive Iterated Extended Kalman Filter for Target Tracking

For the iterated extended Kalman filter (IEKF) in target tracking, the system model and noise estimation are always uncertain. In view of these problems, an improved adaptive iterated extended Kalman filter is proposed. The new algorithm is based on IEKF, combines the improved strong tracking filter to make it more fitting the maneuvering target tracking issue. Moreover, in our approach, the noise variance is adjusted in real-time by a noise parameter estimator which is based on the seasonable statistic characteristic of the noise. The estimator can availably reduce the influence of the time-varying noise. The simulation results indicate that the improved algorithm has higher estimation accuracy on the target position and speed for target tracking.