Two-Layer IMM Tracker with Variable Structure for Curvilinear Maneuvering Targets

Abstract

It is of great importance to develop a robust and fast tracking algorithm for curvilinear maneuvering targets in tracking system. To target this issue, a novel two-layer interacting multiple model (IMM) tracker with variable structure is proposed, in which a nested inner layer IMM and an out layer IMM are executed in loops to boost the tracking performance. The purpose of inner layer IMM, which consists of constant angular velocity model and constant angular acceleration model, is to predict possible turn rate of the moving target. And the goal of outer layer IMM, which is based on curvilinear model with time-varying mode-set that consists of three adaptive turn rates, is to boot robust tracking performance in the presence of measuring noise and target maneuvering. Additionally, the state space in curvilinear model is extended from two-dimension to three-dimension which include position, velocity and acceleration variables. Experimental results over a flight scenario showed that for the specific tracking problem of maneuvering targets, the proposed two-layer IMM tracker with variable structure outperforms the state-of-the-art tracking algorithms significantly.