The Kernel-SME filter for multiple target tracking

We present a novel method for tracking multiple targets, called Kernel-SME filter, that does not require an enumeration of measurement-to-target associations. This method is a further development of the symmetric measurement equation (SME) filter that removes the data association uncertainty of the original measurement equation with the help of a symmetric transformation. The key idea of the Kernel-SME filter is to define a symmetric transformation that maps the measurements to a Gaussian mixture function. This transformation is scalable to a large number of targets and allows for deriving a Gaussian state estimator that only has a cubic runtime complexity in the number of targets.