Optimized Sage–Husa filtering method for multitarget tracking with unknown detection profile

Abstract

The Sage–Husa filter can estimate states of multitarget from available measurements. To address the imprecise estimations of the conventional Sage–Husa filter, an optimized method and its implementation are put forward in this study. Unlike previous approaches, the beta distribution for unknown detection profile is improved, and the transfer probability is applied to update the implicit probability of detection. With respect to the positive definiteness of the estimated covariance, the Cholesky decomposition is used in both prediction and update of the Sage–Husa filter. Recalling the estimated probability of detection, the track gate strategy in the proposed filtering framework is derived to distinguish clutter-generated and target-generated measurements. On the basis of updated measurements, both the state and the track of multitarget are achieved. Finally, the experiments of multitarget tracking are made to indicate the performance of the proposed Sage–Husa filtering method.