Abstract: Large amount of real-time data is detected by various instruments and devices from urban roadway traffic systems. Currently, little information has been utilized from the tremendous wealth of information that can be potentially extracted from these data. Thus, it is extremely important and necessary to study how to utilize the information data resource. This paper presents a quantify measure model of traffic status according to a characteristic figure, which is based on the analysis of RTMS real-time data of Beijing freeway and traffic flow theory and statistics analysis method. The model was used in traffic characteristic analysis of the Second Ring Road, the Third Ring Road and the Fourth Ring Road of Beijing, and some significant performance measures have been achieved. On the other hand, multi-component Gauss mixture models were used for the estimation of the distribution of traffic flow parameters and the distribution parameters were estimated by the EM algorithm. The authors also validate the rationality and reliability of these performance measures.

Key words: urban freeway traffic, characteristic figure, RTMS data, quantify measure, Gaussian mixture model

摘要： 各种仪器设备采集了大量的城市道路交通实时信息数据，但目前所能利用的信息仍较为稀少。研究如何利用这些丰富的信息数据资源极具意义,也十分必要。本文基于对北京市快速干道实时采集的RTMS数据的分析，以交通流理论为基础，结合统计分析方法提出一种基于特征图的道路交通状况量化评价指标模型。具体将模型应用于北京市二、三、四环的交通状况分析，取得了具有一定实际应用意义的量化评价指标。最后，应用多成份Gauss混合模型对交通流参数的分布实施拟合，并采用EM算法进行参数估计，就指标的合理性和可信性做出了进一步的评价分析。

关键词: 城市道路交通, 特征图, RTMS数据, 量化指标, Gauss混合模型