Joint tracking and identification algorithms for multisensor data

Abstract

The paper describes an algorithm to jointly form a track and assign an identity flag to a target on the basis of measurements provided by a suite of sensors: surveillance radar, high resolution radar and electronic support measures. The algorithm is built around Bayes' inference and Kalman filters with the interacting multiple model. The improved performance in the track formation and identity estimation, which accrues by the joint tracking and identification algorithm, is evaluated by Monte Carlo simulation and compared to the performance of filters that process the data provided by each single sensor. The joint tracking and identification algorithm plays an important role in modern surveillance systems with non-cooperative target recognition capabilities.