Effective data association scheme for tracking closely moving targets using factor graphs

Abstract

Effectiveness of tracking closely moving targets depends on the capability to resolve the ambiguity in associating measurements-to-tracks. Joint probabilistic data association (JPDA) has been shown to be very effective in tracking closely moving objects, but the approach is susceptible to track coalescence. The factor graph (FG) based association scheme developed in this paper circumvents the track coalescence by avoiding multiple hypothesis equivalence with recursive updation of likelihood values. The improvement in association using factor graph based data association scheme over JPDA has been demonstrated using a simulated scenario of closely moving targets. The steady state likelihood values obtained at the end of recursive process are shown to match the likelihoods obtained from measurements.