一种基于蝙蝠算法的多目标跟踪数据关联方法  

A bat algorithm based data association method for multi-target tracking

作　　者：王宇杰 李宇[1,2] 黄海宁[1,2] WANG Yujie;LI Yu;HUANG Haining(The Institute of Acoustics of the Chinese Academy of Sciences,Beijing 100190,China;Key Laboratory of Science and Technology on Advanced Underwater Information of the Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院声学研究所,北京100190 [2]中国科学院先进水下信息技术重点实验室,北京100190 [3]中国科学院大学,北京100049

出　　处：《声学技术》2020年第1期98-103,共6页Technical Acoustics

基　　金：国家重点研发计划项目(2018YFC14059);国家自然科学基金项目(11504402)。

摘　　要：针对多目标跟踪中的数据关联问题,提出了基于蝙蝠算法的数据关联方法。首先将多目标数据关联问题建模成组合优化问题,结合数据关联的特点,对蝙蝠算法的搜索更新规则进行改进,使其可以应用于多目标的数据关联问题,并给出了基于蝙蝠算法的多目标数据关联的详细流程。通过仿真实验和被动声呐实测数据测试表明,基于蝙蝠算法的多目标数据关联方法切实可行并且具有较好的效果。A method based on Bat Algorithm to deal with the data association problem for multi-target tracking is proposed.First,the multi-target data association problem is transformed into a combinational optimization problem by modeling,and then the search and update rule of the bat algorithm is improved by combing the characteristics of multi-target data association.The new version of the bat algorithm can be applied to solving multi-target data association problems.And in this paper,the detailed process of the bat algorithm based multi-target data association method is presented.Simulation results and test data of passive sonar show that this algorithm is feasible and effective.

关 键 词：蝙蝠算法 组合优化 被动声呐 多目标跟踪 数据关联 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]