摘要
为了解决单传感器在道路监测中存在的局限性以及交通环境多样化等问题,基于模糊集理论的一种目标决策标准对传统的数据融合算法进行改进。该方法利用决策层模糊集理论的多传感器融合算法对交通目标进行跟踪,采用Z型隶属函数用于决策分支的优化。与传统的算法相比,改进后的数据融合算法对雷达航迹冗余、视频干扰和目标分割等问题都有所改善,并且进一步提高了跟踪精度。收集了大量的实际交通数据来验证雷达和视频跟踪算法的有效性,实验结果表明多传感器融合算法优于单传感器的目标跟踪算法。
In order to address the limitations of single sensor in road monitoring and the diversification of traffic environment,a fuzzy set theory based target decision criterion is proposed to improve the traditional data fusion algorithm.The method utilizes a multi-sensor fusion algorithm with decision-level fuzzy set theory for traffic target tracking,and further,a Z-type affiliation function is used for the optimization of decision branches.Compared with the traditional algorithm,the improved data fusion algorithm improves such problem as radar track redundancy,video interference and target segmentation,and further improves the tracking accuracy.A large amount of actual traffic data is collected to verify the effectiveness of the radar and video tracking algorithms.The experimental results show that the multi-sensor fusion algorithm outperforms the single-sensor target tracking algorithm.
作者
孙景荣
刘思奇
张华
魏晨依
宋诗斌
SUN Jingrong;LIU Siqi;ZHANG Hua;WEI Chenyi;SONG Shibin(School of Aerospace Science and Technology,Xidian University,Xi an 710071,China;Shandong Provincial Key Laboratory of Robot and Intelligent Technology,Shandong University of Science and Technology,Qingdao 266590,China)
出处
《电讯技术》
北大核心
2023年第10期1567-1573,共7页
Telecommunication Engineering
基金
国家自然科学基金面上项目(62071363)
山东省机器人与智能技术重点实验室开放课题研究项目(2021001)
交通运输行业重点科技项目(zzkj-2022-10)。
关键词
智能交通系统
交通目标跟踪
多传感器数据融合
决策级融合
时空匹配
intelligent traffic system
traffic target tracking
multi-sensor data fusion
decision level fusion
space-time matching
