论文信息 - Comparison of two IMM tracking and classifier architectures based on Extended and Unscented Kalman Filter with CRLB

Comparison of two IMM tracking and classifier architectures based on Extended and Unscented Kalman Filter with CRLB

On the basis of the BT kinematics model it is possible to build up an interactive multiple model (IMM) for target tracking using EKFs and UKFs. The performance evaluation (accuracies and classification) of the designed IMM tracking algorithm is predicted via Monte Carlo simulation and compared with the CRLB achievable for the same study case

A. Farina | S. Immediata | L. Timmoneri | D. Vigilante | M. Meloni

[1] Branko Ristic,et al. A comparison of two Crame/spl acute/r-Rao bounds for nonlinear filtering with P/sub d/<1 , 2004, IEEE Transactions on Signal Processing.

[2] Branko Ristic,et al. Cramer-Rao bound for nonlinear filtering with Pd<1 and its application to target tracking , 2002, IEEE Trans. Signal Process..

[3] S. Immediata,et al. Detection and tracking of ballistic target , 2004, Proceedings of the 2004 IEEE Radar Conference (IEEE Cat. No.04CH37509).

[4] Hugh F. Durrant-Whyte,et al. A new method for the nonlinear transformation of means and covariances in filters and estimators , 2000, IEEE Trans. Autom. Control..

[5] S. Immediata,et al. Comparison of recursive and batch processing for impact point prediction of ballistic targets , 2005, IEEE International Radar Conference, 2005..

[6] Yaakov Bar-Shalom,et al. Estimation and Tracking: Principles, Techniques, and Software , 1993 .

[7] Jeffrey K. Uhlmann,et al. Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.