Two-Layer Particle Filter for Multiple Target Detection and Tracking
Ángel F. García‐Fernández, Jesús Grajal, Mark R. Morelande · IEEE Transactions on Aerospace and Electronic Systems · 2013
The detection and tracking of an unknown number of targets using a Bayesian hierarchical model with target labels is presented. To approximate the posterior probability density function (PDF), we develop a two-layer particle filter (PF). One deals with track initiation, and the other deals with track maintenance. In addition the parallel partition (PP) method is proposed to sample the states of the surviving targets.