集中式多传感器不敏多假设滤波算法  

A Centralized Multi-Sensor Unscented Multiple Hypothesis Tracking Algorithm

作　　者：管旭军[1,2] 张玉玲[2] 芮国胜[1] 周旭[1] 

机构地区：[1]海军航空工程学院 [2]中国人民解放军92854部队

出　　处：《电光与控制》2010年第10期79-83,共5页Electronics Optics & Control

基　　金：国家自然科学基金资助项目(60672139)

摘　　要：为了解决非线性系统中杂波环境下的多传感器多目标跟踪问题,提出了一种集中式顺序多传感器不敏多假设滤波算法。在算法中,首先根据顺序结构多传感器系统实现方法将研究问题转化为顺序处理多个非线性单传感器多目标跟踪问题,然后结合多假设跟踪的思想将单传感器中量测点迹与多个航迹互联,在此基础上采用不敏卡尔曼滤波完成非线性条件下目标状态估计与协方差的递推。仿真结果表明,与MSJPDA/EKF算法相比,本算法具有更高的跟踪精度和稳定性。In order to solve the problem of multi-sensor multi-target tracking in nonlinear system in the presence of clutter,a Centralized Multi-Sensor Unscented Multiple Hypothesis Tracking Algorithm（CMSUMHT） is proposed.In the new algorithm,the problem of interest is first converted into multiple nonlinear single-sensor multi-target tracking problems,which can be dealt with sequentially.Then the association of measurements to tracks is implemented according to the principle of multiple hypothesis tracking.Based on this,Unscented Kalman Filter（UKF） is used for the propagation of state distribution in nonlinear system.Simulation results indicate that the accuracy and robustness of proposed algorithm are improved compared with the MSJPDA/EKF algorithm.

关 键 词：多假设跟踪 多目标 多传感器 不敏卡尔曼滤波 非线性 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TN956[电子电信—信号与信息处理]