Modified Two-Filter Smoothing Method for Complex Nonlinear Target Tracking
Chunxia Li, Mingxing Li, Zhang De, Liu Hai, Yanmin Chen · 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · 2019
To improve target state estimate accuracy, two-filter smoothing method is generally utilized. With the method, it needs to acquire the inverse function of target dynamic motion. However, it is difficult to obtain the inverse function when the target motion is complex nonlinear. Though the inverse function can be obtained in some cases, it may leads to incorrect backward transition of target state. In this paper, a new state space model is presented for the backward smoothing by introducing static equation and pseudo-measurement. With the proposed model, the inverse function is avoided to be calculated. Meanwhile, under the new model, all filtering algorithms based on state space model can be utilized for backward smoothing. Taking EKF as an example, the EKF implementation algorithm for two-filter smoothing is derived with the proposed model. The effectiveness and superiority of the proposed technique are validated by the results of the corresponding numerical simulations.