An Adaptive Kalman Filtering Tracking Algorithm Based on Improved Strong Sracking Filter

Adaptive maneuvering target tracking has important significance in the field of target tracking. In this paper, we present an adaptive Kalman filtering tracking algorithm based on improved strong tracking filter (STF). By changing the structure of STF, we apply it to maneuvering target tracking. This greatly expands the range of STF's applications, effectively improves the Kalman filter's ability to adapt to changes of the model. By Monte Carlo simulation, we give the algorithm simulation data matching the measurement noise variance, verify that the algorithm still has a good filtering accuracy when the initial measurement noise covariance error is large. Further more, we verify this algorithm can quickly converge and maintain a high tracking accuracy when the target maneuvers which we mean that system noise mutations.