A comparison of joint/independent state particle filters for tracking closely spaced targets in clutter

In this paper, we present an overview of the literature for particle filtering under measurement origin uncertainty with an emphasize on single scan data association algorithms. We compare some of the existing and newly proposed joint state particle filtering algorithms for the closely spaced target tracking problem. Both maximum a posteriori (MAP) and minimum mean square error (MMSE) estimation outputs of four different algorithms are compared. We also include MMSE outputs of a non-joint (independent) state particle filter and Kalman filter in the comparison as a baseline.