Auxiliary Unscented Particle Cardinalized Probability Hypothesis Density

The probability hypothesis density (PHD) filter has been recently introduced by Mahler as a relief for the intractable computation of the optimal Bayesian multi-targetfiltering. It propagates the posterior intensity of the random finite set (RFS) of targets in time. Despite serving as a powerfuldecluttering algorithm, PHD filter still has the problem of largevariance of the estimated expected number of targets. The cardinalized PHD (CPHD) filter overcomes this problemthrough jointly propagating the posterior intensity and the posterior cardinality distribution. Unfortunately, the particlefilter implementation of the CPHD filter suffers from lack of anefficient method for boosting its efficiency other than the inefficient Bootstrap particle filter. We propose auxiliaryunscented particle implementation of the CPHD filter as a solution to this problem. Numerical simulations indicate significant improvement in the estimation accuracy of the proposed algorithm over the available Sequential Monte Carlo (SMC) implementation of the CPHD filter.