随机有限集推理动目标轨迹的相干累积检测法  

Coherent integration with random finite set inferred trajectories for detecting maneuvering targets

作　　者：杨文彬 李旦 张建秋 YANG Wenbin;LI Dan;ZHANG Jianqiu(School of Information Science and Technology,Key Laboratory of EMW Information,Fudan University,Shanghai 200433,China)

机构地区：[1]复旦大学信息科学与工程学院电磁波信息科学教育部重点实验室,上海200433

出　　处：《系统工程与电子技术》2023年第12期3781-3791,共11页Systems Engineering and Electronics

基　　金：国家自然科学基金(11827808)资助课题

摘　　要：长时间相干累积技术在提高雷达对动目标探测能力方面发挥着重要的作用。但是,由目标机动导致的距离和/或多普勒频率徙动将会大大降低相干累积的性能。为解决上述问题,提出一种随机有限集推理动目标运动轨迹的相干累积检测法。首先,通过频率轴反转变换,提取出描述目标运动特性的信号。然后,利用该信号时频变换后的结果构成测量随机有限集,并以状态空间模型描述各目标的运动,在贝叶斯滤波的框架下实现目标运动轨迹的推理。最后,基于推理的轨迹设计出二维匹配滤波器,来补偿未知的距离和/或多普勒频率徙动。理论分析和数值仿真实验结果均表明,该方法可有效处理具有复杂甚至未知运动形式的机动目标。Long-time coherent integration technique is one of the most important methods for the improvement of radar detection ability of maneuvering targets,whereas the coherent integration performance may be greatly decreased by the range migration(RM)and/or Doppler frequency migration(DFM).A moving target detector with random finite set inferred motion trajectories is proposed to solve the problem above.Firstly,with the frequency axis reversal transform,the signal describing the motion features of the maneuvering targets is obtained.Secondly,when the time-frequency transformation results of the signal are transferred to the observation random finite sets and the target trajectories are described by the state-space model,the motion trajectories of targets can be inferred under the Bayesian filter framework.Finally,based on the inferred target trajectories,the two-dimensional matched filters can be designed to compensate the unknown RM and/or DFM.Theoretical analysis and numerical simulation experiments verify that the proposed method can be applied to maneuvering targets with complex or even unknown motion forms effectively.

关 键 词：脉冲多普勒雷达 匹配滤波 随机有限集 距离徏动 多普勒频率徏动 

分 类 号：TN957[电子电信—信号与信息处理]