Out-of-sequence measurement algorithm based on Gaussian particle filter

Out-of-sequence-measurements problem tend to arise in multi-sensors target tracking, due to communication delays and varying signal pre-processing time. A number of studies have addressed the processing of out-of-sequence-measurements when the target dynamics and measurement models are linear or nonlinear. To solve this problem more effectively, a novel out of sequence measurement processing algorithm is developed and presented in this study. It based on sequential Bayesian formula and Gaussian particle filter. In essence, this algorithm uses importance sampling to update the posterior means and their covariances and also approximates the posterior distributes by single Gaussians. Both theoretical analysis and simulation results show that it has low complexity, its performance is consistent with standard sequential processing algorithm and it is asymptotically optimal as numbers of particles tends to infinity. © 2010 Asian Network for Scientific Information.