Maneuvering Target Tracking in Dense Clutter Based on Particle Filtering

Abstract

An improved particle filtering (IPF) is presented to perform maneuvering target tracking in dense clutter. The proposed filter uses several efficient variance reduction methods to combat particle degeneracy, low mode prior probabilities and measurement-origin uncertainty. Within the framework of a hybrid state estimation, each particle samples a discrete mode from its posterior distribution and the continuous state variables are approximated by a multivariate Gaussian mixture that is updated by an unscented Kalman filtering (UKF). The uncertainty of measurement origin is solved by Monte Carlo probabilistic data association method where the distribution of interest is approximated by particle filtering and UKF. Correct data association and precise behavior mode detection are successfully achieved by the proposed method in the environment with heavy clutter and very low mode prior probability. The performance of the proposed filter is examined and compared by Monte Carlo simulation over typical target scenario for various clutter densities. The simulation results show the effectiveness of the proposed filter.