低采样率浮动车的路况计算精度优化

Improving Accuracy of Traffic Situation Estimation for Low-sampling-rate Floating Car

路口和立交桥作为城市路网的重要组成部分,对于路况计算具有重大的意义.本文为了解决复杂城市道路场景下,低采样率的车辆轨迹数据计算出的路况精度较差的问题,提出一种改进的路况计算精度优化算法.首先针对路况计算精度较差的立交桥区域,将复杂的立交桥抽象成一个路口,通过改进的聚类算法对立交桥进行了自动化定位.然后利用凸包算法划分了立交桥的路口范围,将复杂路口路况简化为转向时间.利用同一辆车经过路口(普通路口和立交桥路口)前后的轨迹点信息来精确推导相关道路和路口路况.实际数据分析表明,该方法可有效提高路况计算精度.

As an important part of urban road network,intersection and overpass are of great significance for traffic situation estimation. In order to solve the problem of poor traffic situation estimation from floating car trajectory data with lowsampling rate in the scene of complex urban road,an improved algorithm for traffic situation estimation is proposed. Firstly,the complex urban overpass is abstracted as an intersection by automatically locating the overpass through an improved clustering algorithm. Then,the convex hull algorithm is used to determine the scope of overpass,and the complex overpass traffic situation is simplified as intersection turning time.Using floating car trajectory passing through intersection( crossroad and overpass),traffic situation around intersection can be accurately deduced. The real floating car data analysis shows that this method can effectively improve the accuracy of urban traffic situation estimation.