Performance of the SME filter in multiple target tracking

This dissertation centers on the continued development of the symmetric measurement equation (SME) filter approach to track maintenance in multiple target tracking. We first consider the case of tracking the x coordinate positions and x coordinate velocities via the SME filter of N (N arbitrary) targets moving in three-dimensional space with constant velocities. Here the data association problem that is inherent in multiple target tracking is eliminated by defining new measurements to be sums of products of the x coordinate measurements. Various analytical properties of the SME filter are studied and in particular we show that under a very weak condition, the unforced part of the estimation error equation of the SME filter is locally exponentially stable. We also demonstrate the performance of the SME filter via computer simulations. We then apply the SME filter approach to the tracking of N targets with spherical coordinate measurements of the target positions. Here the new measurements are defined to be sums of products of the Cartesian coordinate measurements that are generated from the spherical coordinate measurements. The stability properties of the resulting SME filter are investigated and the performance of the filter is examined via computer simulations.