Multisensor tracking of multiple maneuvering targets using multiscan JPDA and IMM filtering

We present a novel suboptimal filtering algorithm developed by applying a multiscan joint probabilistic data association (Mscan-JPDA) technique and interacting multiple model (IMM) filtering approach. In the past this algorithm has been restricted to single sensor tracking which we now extend to a multiple sensor tracking scenario. Multiscan JPDA addresses the problem of measurement-to-track data association for multiple targets and clutter. An IMM approach is exploited to consider the tracking of highly maneuvering targets. The proposed algorithm is illustrated via a simulation example involving tracking of two maneuvering targets by two sensors (radar and infrared) and a multiscan data window of length two.