The Kalman-Levy filter and heavy-tailed models for tracking manoeuvring targets

The assumption of Gaussian system and measurement noise models has been standard practice for target tracking algorithm development for many years. For problems involving manoeuvring targets or groups of interacting targets this is known to be an over-simplification and a potentially poor approximation. In this paper the use of heavy-tailed noise models coupled with simple dynamics is considered as a means of capturing the non-Gaussian behaviour of targets. A recently published approximate technique called the Kalman-Levy filter is used for track maintenance. Performance of a heavy-tailed system model implemented via the Kalman-Levy filter is compared against an IMM for two sample trajectories taken from a benchmark problem.