基于卡口数据的交通参数提取方法研究

A Traffic Parameter Extraction Method Based on Checkpoint Data

针对交通参数提取繁琐及流程混乱问题,提出了数据预处理-指标提取-可视化一体的交通卡口数据挖掘流程。针对传统断面数据无法获取过饱和状态交通参数的缺陷,通过深入挖掘卡口数据蕴含的时间关联信息,并结合路网空间逻辑关系,基于Pandas和NumPy工具包构建了行程时间、平均车速和车辆延误提取模型,进而利用时空轨迹图研究了过饱和状态下的最大排队长度测算方法,该方法使用延误、流量、车速参数均为实时提取,实现了主动全时状态提取;以淄博市实际道路卡口数据为例验证了模型的有效性,结果显示,排队长度的准确率达85%以上;基于Python可视化库和Echarts对数据分析结果进行可视化处理,实现了交通需求及状态数据的动静态展现,能够为智能交通管控的决策提供支撑。

In order to solve problems of tedious traffic parameter extraction and confusing processes,a process of traffic checkpoint data mining including integrating data preprocessing,index extraction,and visualization is proposed.Aiming at a defect that traditional cross-section data cannot obtain supersaturated traffic parameters,through deeply mining the time correlation information contained in bayonet data and combining with spatial logic relationship of road network,an extraction model of road network time,average speed,and vehicle delay is established based on Pandas and NumPy.The maximum queue length measurement method under the oversaturated statues is studied by the space-time trajectory map.In this method,the parameters of delay,flow,and speed are all extracted in real time,and active full time state extraction is achieved.Taking the actual road checkpoint data in Zibo City as a case study,the effectiveness of the model is verified,and the results show that the accuracy rate of queue length is more than 85%.The results of data analysis are visualized to realize the dynamic and static display of traffic demand and state data based on Python visualization library and Echarts,which can provide support for the decision-making of intelligent traffic management and control.