Track Segment Association Based on Expectation-Maximization Algorithm for Joint Estimate and Identification

Abstract

Modern target tracking system are facing the challenge of track breakages frequently. The track segment association (TSA) technique for judging the identitiy of two fractured tracks is becoming increasingly important because the continual tracking performance is important because the continual tracking performance is important for intelligence report. In this paper, we propose one consider a common situation of track breakages due to target maneuver with turn motion. The coordinated turn maneuver was described by the turn rate. The estimation of maneuvering model parameter and stitching start time and end time (namely, start and end time of maneuver) both are needed by the fact that these two problems are critical for TSA and coupled with each other. A novel schema with the tought of joint estimate and identification of stitching time and model parameter are presented based on the expectation-maximization (EM) algorithm. The simulation shows the effect of the proposed method in broken tracks reduction and track continuity improvement.