14.5 Performance of Kalman Class DIFAR Track Estimators

The track estimators used for the DIFAR case study include the EKF, UKF, SSKF, GHKF, and MCKF. In this section, we compare the DIFAR tracking x-axis and y-axis RMS errors for each track estimator. Figures 14.314.7 show the RMS x-axis and y-axis RMS errors for the five different track algorithms, along with the CRLB, for signal SNRs from 20 dB down to 0 dB in increments of 5 dB. One can immediately see from these figures that there is very little difference among the tracker algorithms when applied to the DIFAR problem at all SNRs. The CRLB is the gray line across the bottom of each figure. Based on these performance measures, for the DIFAR problem, one should use the EKF since it minimizes the computational burden. It is readily apparent from these figures that for all SNRs the filters have their best performance when the target ship enters the buoy field near the img position. But when the target is far from the buoy field, track performance degradation increases with range from the buoy field center and decreasing SNR. In addition, at an SNR of 5 dB or below, the SSKF tracker became unstable. At an SNR of 0 dB, the MCKF also became unstable. These cases are not included in the RMS plots.

Figure 14.3 Comparison of the RMS errors for five different track estimation algorithms with the signal SNR at 20 dB.

Figure 14.4 Comparison ...

Get Bayesian Estimation and Tracking: A Practical Guide now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.