Multitarget association and tracking in 3-D space based on particle filter with joint multitarget probability density

This paper addresses the problem of 3-dimensional (3-D) multitarget tracking using particle filter with the joint multitarget probability density (JMPD) technique. The estimation allows the nonlinear target motion with unlabeled measurement association as well as non-Gaussian target state densities. In addition, we decompose the 3-D formulation into multiple 2-D particle filters that operate on the 2-D planes. Both selection and combining of the 2-D particle filters for 3-D tracking are presented and discussed. Finally, we analyze the tracking and association performance of the proposed approach especially in the cases of multitarget crossing and overlapping.