摘要
在进行城市道路交通流量调查及部分重要路网节点、交叉口交通数据采集时,采用低频数据收集方式会使车辆轨迹匹配精度低、交通流量数据误差大。通过研究隐式马尔可夫理论及最小费用最大流模型,提出一种车辆轨迹重构方法。该方法利用多源数据融合技术以及地理信息定位匹配技术,对无检测器路段缺失的各项交通基础数据进行合理的演进推算,为车辆轨迹重构研究提供重要的数据支撑。利用成都市某区域出租车的高频轨迹点位数据集进行验证。结果表明,利用车辆低频轨迹点位进行轨迹重构的完全覆盖率达到了89.4%,验证了所提出的车辆轨迹重构方法的有效性及可行性。
Focused on low accuracy in vehicle trajectory matching and traffic flow data errors,when low-frequency collection approach was used during the survey of urban road traffic flow and traffic data collection of particularly at critical road network nodes.A vehicle trajectory reconstruction method was proposed based on the study of the hidden Markov theory and the minimum cost maximum flow model.Using multi-source data fusion technology and geographic information positioning matching technology,the missing traffic basic data of the non-detector road section were reasonably estimated to provide important data support for the research of vehicle trajectory reconstruction.Then,a highfrequency trajectory point dataset of taxi vehicles in a specific region of Chengdu City was employed to validate the effectiveness of this method.The results demonstrate that the complete coverage rate of trajectory reconstruction using low-frequency vehicle trajectory points reaches 89.4%,confirming the method's efficacy and practicality.
作者
帅庆珍
张家铭
周凤
SHUAI Qingzhen;ZHANG Jiaming;ZHOU Feng(College of Traffic and Transportation,Chongqing Jiaotong University,Chongqing 400074,China;JSTI Group,Nanjing 210018,China;College of Life Science,Yangtze University,Jingzhou 434025,China)
出处
《交通科学与工程》
2024年第2期146-153,共8页
Journal of Transport Science and Engineering
基金
重庆市科学技术协会项目(2018KXKT06)。
关键词
车辆低频轨迹数据集
最小费用最大流
多源数据融合
轨迹重构
vehicle low-frequency trajectory dataset
minimum cost maximum flow
multi-source data fusion
trajectory reconstruction
