关键词: 信号处理, Rao-Blackwellized粒子概率假设密度滤波算法, 仿真, 混合线性/非线性, 多目标跟踪

Abstract: In this article, a new random set based on the probability hypothesis density filtering algorithm called the Rao-Blackwellized particle probability hypothesis density filter (RBP-PHDF) is proposed for multi-target tracking (MTT) application. The algorithm, while utilizing the idea of Rao-Blackwellized to enhance the estimating performance of the probability hypothesis density (PHD), adopts the sequential Monte Carlo (SMC) method to predict and estimate the nonlinear states of the multiple targets. In addition, the linear states are estimated by the Kalman filter (KF) with the information embedded in the estimated nonlinear states. Simulation results of the proposed method in multi target tracking environment show that, in addition to reducing particle dimensions and computation complexity, the proposed method significantly enhances tracking accuracy according to the item of miss distance as compared with the results obtained by current sequential Monte Carlo probability hypothesis density filter (SMC-PHDF).

Key words: signal processing, Rao-Blackwellized particle probability hypothesis density filter, simulation, mixed linear/nonlinear, multitarget tracking