状态与杂波相关的GM-PHD平滑滤波  

GM-PHD smoothing filter with state-dependent clutter

作　　者：陈金广[1,2,3] 王星辉[1,2,3] 马丽丽 CHEN Jin-guang;WANG Xing-hui;MA Li-li(School of Computer Science,Xi’an Polytechnic University,Xi’an 710048,China;Shaanxi Key Laboratory of Clothing Intelligence,Xi’an Polytechnic University,Xi’an 710048,China;State and Local Joint Engineering Research Center for Advanced Networking and Intelligent Information Services,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学计算机科学学院,陕西西安710048 [2]西安工程大学陕西省服装设计智能化重点实验室,陕西西安710048 [3]西安工程大学新型网络智能信息服务国家地方联合工程研究中心,陕西西安710048

出　　处：《计算机工程与设计》2019年第11期3186-3191,共6页Computer Engineering and Design

基　　金：陕西省教育厅科研计划基金项目(18JK0349);西安工程大学研究生创新基金项目(chx201813)

摘　　要：考虑到多目标跟踪中杂波与状态之间的相关性,引入平滑算法提高目标估计的精度。针对整个监视区域内的杂波,重新计算其强度;将目标分为幸存目标和新生目标两大类,采用自适应椭球门限对量测进行预处理,将门限内的量测用于更新幸存目标,门限外的量测用于更新新生目标;采用RTS平滑算法进行逆向平滑。实验结果表明,在该条件下所提算法具有较好的跟踪性能,优于未平滑的GM-PHD滤波器。Considering the correlation between clutter and state in multi-target tracking,a smoothing algorithm was introduced to improve the accuracy of target estimation.The clutter intensity in the whole surveillance area was recalculated.Targets were divided into two categories,i.e.,surviving targets and new targets.The adaptive ellipsoid threshold was used to preprocess measurements.The measurements within the threshold were used to update the surviving targets.The measurements outside the threshold were used to update the new targets.The RTS smoother was used to reverse smoothing.Experimental results show that the proposed algorithm has better tracking performance under this condition,and it is superior to GM-PHD filter in unsmooth state and clutter related environment.

关 键 词：多目标跟踪 RTS平滑 概率假设密度滤波 状态相关杂波 自适应椭球门限 

分 类 号：TP931[自动化与计算机技术]