基于状态可观测性和多模态数据PF的移动目标跟踪  

Moving Target Tracking Based on State Observability and Multimodal Data PF

作　　者：胡国华[1] 赵涓涓 郝耀军[1] HU Guohua;ZHAO Juanjuan;HAO Yaojun(Department of Computer,Xinzhou Normal University,Xinzhou 034000,China;College of Information and Computer,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]忻州师范学院计算机系,山西忻州034000 [2]太原理工大学信息与计算机学院,山西太原030024

出　　处：《无线电工程》2024年第6期1504-1511,共8页Radio Engineering

基　　金：山西省自然科学基金(20210302124330);山西省高校科技创新项目(2019L0847);教育部人文社科青年基金项目(20YJC630034);忻州师范学院五台山文化生态研究院专题项目(2020133101)。

摘　　要：为了实现对移动目标的跟踪,提出了一种新颖的基于目标状态可观测性和多模态数据粒子滤波(Particle Filter,PF)的跟踪方案。通过部署在目标移动区域中的传感器获得跟踪目标的距离和到达方向测量值,对接收到的数据进行预处理来计算PF的观测值,以形成一个临时距离图像。通过利用状态更新函数和形成的候选图像模板确定目标状态向量;在PF器中加入额外的加权阶段,使得PF器可自适应地同步多模态数据流,以实现鲁棒的目标跟踪。仿真实验结果验证了所提方案能够有效地跟踪移动目标。In order to track moving targets,a novel tracking scheme based on the observability of target state and multimodal data Particle Filtering(PF)is proposed.Using the measurements of the distance and direction of arrival for the tracking target obtained by the sensors deployed in the target moving region,the particle filtering observation value is calculated by preprocessing the received data to form a temporary range image.Then the target state vector is determined by using the state update function and the formed candidate image template.In addition,an additional weighted stage is added to the particle filter,so that the particle filter can adaptively synchronize the multimodal data stream to achieve robust target tracking.The simulation results show that the proposed scheme can track the moving target effectively.

关 键 词：无线传感器网络 移动目标跟踪 状态向量 粒子滤波 多模态数据 传播延迟 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]