检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:张韦华 吕辰 孙琳 ZHANG Weihua;LÜChen;SUN Lin
机构地区:[1]南京云析科技有限公司,江苏南京210000 [2]江苏中路交通发展有限公司,江苏无锡214026
出 处:《智能城市》2025年第1期21-25,共5页Intelligent City
摘 要:城市交叉口作为道路交通的常发性瓶颈节点,在调节、梳理和控制道路交通的过程中发挥着重要作用。利用现代信息技术全面感知交叉口交通运行状态,实现城市交通管理系统的智能化,是当前交通管理研究的重要课题。文章提出一种基于低空域无人机航拍视频的交叉口全景感知方法,利用YOLOv5和Deep SORT算法构建交通目标检测和跟踪模型,精确识别视频范围内的动静态交通要素,智能提取动态交通要素在交叉口的全域轨迹信息,为交叉口的精细化智能交通管控提供数据支撑。该方法在珠海市两个道路交叉口进行了验证。结果表明,车辆检测和跟踪结果的精度均达到99.8%。该方法具有可靠、便捷、适用范围广等特点,为大数据环境下的交通管控提供了新的感知分析模式。Urban intersections,as common bottleneck nodes in road traffic,play a crucial role in regulating,organizing,and controlling traffic flow.Utilizing modern information technology to comprehensively perceive the traffic operation status at intersections and achieving the intelligent management of urban traffic systems is an important research topic in current traffic management.This paper proposes a panoramic perception method for intersections based on low-altitude drone video footage.By constructing a traffic target detection and tracking model using the YOLOv5 and Deep SORT algorithms,this method accurately identifies static and dynamic traffic elements within the video range and intelligently extracts the global trajectory information of dynamic traffic elements at the intersection,providing data support for refined intelligent traffic control at intersections.The method was verified at two road intersections in Zhuhai City.The results show that the accuracy of vehicle detection and tracking results is above 99.8%.This method is characterized by reliability,convenience,and broad applicability,offering a new perception and analysis model for traffic control in the context of big data.
关 键 词:无人机 交叉口 车辆检测与跟踪 YOLOv5 Deep SORT
分 类 号:U495[交通运输工程—交通运输规划与管理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.137.198.25