A novel track initiation method for track splitting and merging

Abstract

A novel efficient method is proposed for the splitting and merging problems of track initiation, an important issue of multiple target tracking. Tack initiation demands that the method should determine the existence and initial state of a target quickly and correctly. There is no doubt that the high density of clutters (false alarm), large measurement errors and missing measurements deteriorate and complicate the track initiation. There are two primary shortcomings for the conventional track initiation methods dealing with the issues mentioned above: (i) they cannot exclude the turbulences of the clutters, (ii) they cannot estimate the initial state for a new confirmed track/target. Based on the MHT (multiple target tracking) principle and modified logic-based track initiation method, our new method can deal with the splitting and merging problems deriving from high density of clutters, large measurement errors and missing measurements; it can determine the target's existence and estimate its initial state with the least squares method. What's more, our method is fully automatic and requires no manual input of any kind for initializing and tuning any parameter. The simulation results indicate that the proposed method performs well for track initiation.