Traffic State Estimationfor Urban Road Network Based On Video Detection System

With the constant improvement of urban infrastructure, intelligent traffic management systems play an increasingly important role in urban traffic management. The wide range of application of Urban Roads Monitoring System has been promoting the development of intelligent transportation and it became an integral part of traffic management process with the function of capturing target vehicles, license plate recognition, traffic statistics, illegal capture, etc.Real-time traffic state is the basis of the Advanced Traffic Information System. It can help to implement the traffic control and management, dynamic route guidance, improve the travel condition and provide the reference for resident trips, bus dispatching and urban planning. At present, traffic state estimation is mostly based on mathematical statistics or pattern recognition, but these methods lack of the combination of subjective and objective. This paper, based on the real-time road travel time, combined with drivers expect to establish traffic condition evaluation method, to realize the combination of the subjective and objective.The whole thesis includes the following parts. First of all, the monitoring system as an important part of intelligent traffic management system, has been widely used in most in Chinese city. Through bayonet can obtain the point time information of the same car, which was carried out on matching the license plate number vehicle and calculating travel time. Due to the working principle of test equipment itself. Also randomness of individual behavior involved in traffic, so there are loss and abnormal situation. In this paper, using the text information acquire from monitoring system to create data base, repair the missing data according to different situations in a reasonable manner, similar to t-test or z-test median deviation method to deal with abnormal data, and then the vehicle’s road travel time is calculated.Accurate travel time is the basic premise of traffic state estimation, reasonable traffic state estimates also need to establish a comprehensive evaluation index. Index based on travel time can easily be understood by traffic participants, travel time can describe traffic state from different time and space dimension according to different requirements; travel time index can not only describe the traffic congestion of specific location appropriate, it can also describe the whole road traffic congestion. The existing traffic state indexes assuming the traffic state of the different road grade is consistent, when the traffic state indexes for individual sections or single vehicle is the same that congestion degree is the same, but management and driver feel not the same to the same traffic state of the different level road, such as velocity in expressway and roads also decreased 20%, managers and drivers think more congested on the expressway, mainly because of the drivers’desired speed and relative speed on the expressways is very high, so it needs to consider the drivers feel when estimate traffic state of the different roads or single vehicle. This paper extends the definition of the indicators to incorporate desired speed distribution and hence, calculate congestion indicators more accurately.The traffic state is divided into five grades, real time traffic status display is realized by programming.Taking trunk Shanda Road-Lishan Road in Jinan as an example, to verify the traffic state evaluation method presented in this paper can more accurately reflect the road traffic condition, traffic condition evaluation index is reasonable.