A PMBM forward-backward smoother for multi-target tracking of point sources

This paper proposes a Poisson multi-Bernoulli mixture (PMBM) forward-backward smoother for robust multi-target tracking of point sources within the random finite sets (RFS) framework. The method operates in two phases: forward filtering and backward smoothing. During forward filtering, the PMBM density is recursively propagated via Bayesian prediction and update. This phase explicitly models target births, deaths, and existence uncertainties, even under high clutter densities. In the backward smoothing phase, state estimates are refined through parametric Bayesian retrodiction. Here, posterior PMBM weights are analytically updated using future measurements, effectively resolving temporal ambiguities. A simulation study is conducted to evaluate the performance of the proposed method, demonstrating its effectiveness in practical scenarios.