基于序贯蒙特卡洛算法的交通流事件重构  

Event reconstruction for traffic flow simulation based on sequential Monte Carlo

作　　者：冯向文 燕雪峰[1] 

机构地区：[1]南京航空航天大学计算机科学与技术学院,江苏南京210016

出　　处：《计算机工程与科学》2016年第9期1812-1817,共6页Computer Engineering & Science

基　　金：十三五重点基础科研项目(JCKY2016206B001)

摘　　要：针对交通数据重构应用性差、缺乏对交通事件重构的研究等问题,结合交通流非线性非高斯的特点,提出一个基于序贯蒙特卡洛方法的交通流堵塞事件重构模型。该模型不断同化道路上的传感器数据,使仿真中的交通状态不断逼近真实路况,通过分析仿真数据以探测真实路网中存在的堵塞事件。模型能够对探测到的堵塞进行多粒子模拟来实现对真实道路上堵塞事件的重构。实验结果表明,该模型能够推测并重构出道路上的堵塞事件,对堵塞起始位置重构的平均误差为17m,对堵塞范围重构的平均覆盖率为82%。Combining with the nonlinear and non Gaussian characteristics of the traffic flow, we pro pose a traffic flow congestion event reconstruction framework based on the Sequential Monte Carlo （SMC） to deal with the congestion reconstruction problem. The simulation＇s states can get close to the real scene continuously when the data assimilation model assimilates the real time sensor data constant- ly. The congestion event in real scene can be estimated based on the simulation data. Thus, the simula- tion model can simulate the congestion via different particle simulations and finally reconstruct the con gestion event. Experimental results show that the framework can detect and reconstruct the congestion event on the real road network; the average error of the start position is 17m, while the average cover- age rate of the congestion range is 82%.

关 键 词：序贯蒙特卡洛算法 动态数据驱动应用系统 交通流仿真 事件重构 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]