基于低频定点检测数据的交叉口交通状态估计  

Traffic State Estimation Based on Low Frequency Detection Data at Intersections

作　　者：唐克双[1] 徐天祥[1] 董可然[1] 李克平[1] 

机构地区：[1]同济大学道路与交通工程教育部重点实验室,上海201804

出　　处：《同济大学学报（自然科学版）》2017年第5期705-713,720,共10页Journal of Tongji University:Natural Science

基　　金："十二五"国家科技支撑计划(2014BAG03B02)

摘　　要：针对我国中小城市数据现状,提出了一种基于路中定点线圈低频(1/60Hz)检测数据的交叉口交通状态估计方法.该方法基于仿真数据,分析了不同环境变量组合条件下占有率、流量和交通状态的关系,并提出了基于线性拟合的交通状态分界线建立方法;又利用多元线性回归拟合出分界曲线各系数与环境变量的函数关系,用其估计一般条件下的交通状态.经过验证,本方法仿真环境和实证环境下的平均估计准确率分别达到80%和75%以上,且严重错误率均低于2.1%.A traffic state identification method for intersections was proposed based on detection data with a low frequency of 1/60 Hz from detection on the mid of the urban roads which was applied for urban interrupted flow in medium and small cities of our country. At first, the relationship among occupation, volume and traffic state was analyzed under different parameters of circumstances based on simulation data and a method of curve fitting was proposed to build the boundaries of different traffic state. Then the functional relationship of coefficients of boundaries functions with environment variables was fit out which was later applied to general ones. The methods above were verified by simulation data with the identification rate of over 80%, and empirical data with the identification rate of over 75% , with severe mistake rates less than 2.1%.

关 键 词：交通状态估计 信号控制交叉口 定点检测器 低频检测数据 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]