Interacting multiple model joint probabilistic data association avoiding track coalescence

For the problem of tracking multiple targets the joint probabilistic data association (JPDA) filter approach has shown to be very effective in handling clutter and missed detections. Elsewhere the problem of track coalescence has been also solved for JPDA. The aim of this paper is to combine this JPDA avoiding track coalescence approach with IMM to track multiple maneuvering targets. The tracking problem is first embedded into one of filtering for a jump linear descriptor system with stochastic coefficients. Next, for this descriptor system, exact filter equations are derived, hypothesis management assumptions are adopted, and IMMJPDA avoiding track coalescence filter equations are developed. Finally, the filter performance is illustrated through Monte Carlo simulations for a simple example.