道路交通拥挤水平分类方法研究

道路拥挤水平是评估交通运行质量和道路网络性能的重要指标之一,对交通规划、路线导航以及道路拥堵管理具有重要参考价值.利用车载移动传感信息与驾驶员判断的一致性,研究一种自动分类道路交通拥挤水平的新方法.利用GPS传感器和CCD摄像机采集路况信息,使用滑动窗口瞬时抽样技术抽象出车辆运行模式.此外,还引入驾驶员对道路交通3种状态(Light,Heavy和Jam)的感知评价信息,将驾驶员感知和车辆运行模式引入到决策树学习算法(J48)中进行训练.

Classification on the level of road traffic congestion

The road traffic congestion level was one of the most important indexes for evaluating the quality of traffic operation and the performance of road networks,it had important reference value for the transportation planning,route navigation and road congestion management.In this paper,a novel approach was used to classify automatically traffic congestion level by using the consistency between the mobile sensor information and the judgments of driver.In the approach,a GPS device and CCD were utilized to collect road information,and a instantaneous sampling technique in a sliding window was adapted to abstract movement pattern of vehicle.Otherwise,the human perceptions were used to rate the traffic congestion levels into three levels: light,heavy,and jam.Then the ratings and velocity were fed into a decision tree learning model(J48).