The invention discloses a road network subarea division method based on electronic police data. The method mainly comprises the steps of firstly, performing data cleaning on original electronic police data with noise data, removing the noise data, and calculating traffic flow parameters of a road section within a time interval according to road section vehicle passing records based on the cleaned electronic police data; secondly, on the basis of the cleaned electronic police data, the moment when the vehicle passes through the upstream and downstream intersection stop line of the road section is obtained, the driving time of the vehicle on the road section within the time interval is corrected accordingly, and the traffic density of the road section within the time interval is calculated in combination with the actual length of the road section; then, based on a complex network theory, constructing an urban network into an undirected graph, nodes correspond to road sections in a road network, analyzing an adjacency relation of the road sections according to a space relation between the road sections, constructing an adjacency matrix at the same time, and calculating a space distance between the nodes according to the adjacency matrix; and finally, calculating the weight between the two nodes by using a Gaussian probability function, carrying out initialization division by using a FastUnfolding algorithm, on the basis, improving a Newman fast algorithm modularity function to enable the Newman fast algorithm modularity function to be suitable for a weighted complex network, and merging initialization sub-region division results to obtain a final road network sub-region division result. According to the method, the problem that an existing road network partitioning method is insensitive can be solved, and more accurate heterogeneous road network subregion partitioning can be achieved.
本发明公开了一种基于电警数据的路网子区划分方法。主要步骤包括:首先,对于存在噪声数据的原始电警数据进行数据清洗,去除噪声数据,基于清洗后的电警数据,根据路段过车记录,计算时间间隔内路段的交通流量参数;其次,基于清洗后的电警数据,获取车辆通过路段上下游交叉口停止线的时刻,据此修正时间间隔内车辆在路段上的行驶时间,并结合路段的实际长度,计算时间间隔内路段的交通密度;之后,基于复杂网络理论,将城市网络构建为无向图,节点对应路网中的路段,并根据路段间的空间关系分析其邻接关系,同时构建邻接矩阵,据此计算节点间的空间距离;最后,使用高斯概率函数计算两节点间的权重,使用Fast_Unfolding算法进行初始化划分,在此基础上,对Newman快速算法模块度函数进行改进,使之适用于加权复杂网络,并对初始化子区划分结果进行合并,得到最终的路网子区划分结果。本发明可以解决现有路网分区方法不灵敏的问题,可实现更准确的异质性路网子区划分。
Road network subarea division method based on electronic police data
一种基于电警数据的路网子区划分方法
2022-12-13
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Novel urban road network dynamic subarea division method
European Patent Office | 2023
|Urban road network signal control subarea division method and device
European Patent Office | 2020
|Urban area road traffic coordination control method based on road network subarea division
European Patent Office | 2023
|Urban area road traffic network subarea division method based on congestion index distribution
European Patent Office | 2023
|European Patent Office | 2023
|