Evaluating the sequential importance re-sampling particle filter for radar target track filtering

Abstract

The paper focuses on the implementation and evaluation of the sequential importance re-sampling particle filter for radar target track filtering of a maneuvering target, through the quantitative simulation and analysis thereof. From the literature it is suggested that particle filters are more suitable in radar target track filtering for non-linear, non-Gaussian maneuvering target tracking problems [3], [7]. Target track filtering, also called target track smoothing, aims to minimize the error between a target's predicted and actual position. The objective of this work has been achieved through the development of a software radar target tracking filter simulator, which implemented a sequential importance resampling (SIR) particle filter algorithm and suitable target and noise models. Predefined metrics identified from the literature, namely the root mean squared error metric for accuracy, and the normalized processing time metric for computational complexity, have been used to evaluate the SIR particle filter. It will be shown that the SIR particle filter achieved improved accuracy performance in the track filtering of a maneuvering target in a non-Gaussian (Laplacian) noise environment, compared to a Gaussian noise environment. It will also be shown that the accuracy performance of the SIR particle filter is a function of the number of particles used in the filter algorithm. The SIR particle filter will be compared to two conventional tracking filters, namely the alpha-beta filter and the Singer-Kalman filter. The results will show that the SIR particle filter outperformed the two conventional filters in the considered test scenarios. The computational complexity of the SIR particle filter is a function of the number of particles used in the filter algorithm, but is typically higher than that of the alpha-beta filter and the Singer-Kalman filter. Analysis of the posterior Cramer-Rao lower bound of the SIR particle filter will be shown.