论文部分内容阅读
为了提高道路交通状态判别精度,提出基于浮动车检测与感应线圈融合技术的道路交通状态判别模型。该模型包括3部分:1)浮动车模块:利用安装在出租车上的GPS定位设备得到道路3部分的行程时间;2)感应线圈模块:利用安装在道路上的感应线圈以及交通信号参数得到道路的行程时间;3)数据融合模块。利用神经网络将以上两模块的结果作为输入从而提高道路交通状态判别的精度。该文利用7 000多辆装有GPS模块的出租车、100个安装在广州市主要道路口上的固定检测器以及广州市电子地图,对提出的模型进行了试验,试验结果表明该模型是有效的,50个数据的均方误差为0.1 s。
In order to improve the discrimination accuracy of road traffic status, a road traffic state discrimination model based on the fusion of floating vehicle detection and induction coil is proposed. The model consists of 3 parts: 1) Floating car module: using the GPS positioning device installed on the taxi to get the travel time of the road 3; 2) Induction coil module: using the induction coil installed on the road and the traffic signal parameters to get the road Of the trip time; 3) data fusion module. The neural network is used to input the result of the above two modules so as to improve the accuracy of road traffic state discrimination. This paper tests the proposed model with more than 7,000 taxis equipped with GPS modules, 100 fixed detectors installed at the main road junctions in Guangzhou, and an electronic map of Guangzhou City. The experimental results show that this model is effective , 50 data mean square error of 0.1 s.