基于宏观基本图的路网交通拥堵甄别方法研究
|
摘要
宏观基本图是道路网络的基本属性,能够直观、准确地反映交通状态变化规律.以路网宏观基本图为基础,结合马尔科夫链模型,提出路网交通拥堵状态判断方法,该方法可根据检测到的路网内车辆数快速甄别交通拥堵状态,对拥堵状态等级临界点附近范围的拥堵甄别结合马尔科夫链模型,提高了判断的精确性.案例分析表明,该方法可行,且具有较好的可靠性.
The Macroscopic Fundamental Diagram(MFD)is the essential attribute of the road network,which can reflect the changing law of traffic state intuitively and accurately.A method of network traffic congestion discrimination was proposed based on macroscopic fundamental diagram and Markov chain model.This method can quickly identify the traffic congestion state based on the number of vehicles detected in the road network.And the method of combining the Markov chain model to discriminate scale in the vicinity of the critical point can greatly improves the accuracy of judgment.The case study shows that the method is feasible and has good reliability.
The Macroscopic Fundamental Diagram(MFD)is the essential attribute of the road network,which can reflect the changing law of traffic state intuitively and accurately.A method of network traffic congestion discrimination was proposed based on macroscopic fundamental diagram and Markov chain model.This method can quickly identify the traffic congestion state based on the number of vehicles detected in the road network.And the method of combining the Markov chain model to discriminate scale in the vicinity of the critical point can greatly improves the accuracy of judgment.The case study shows that the method is feasible and has good reliability.
引文
[1]姜桂艳.道路交通状态判别技术与应用[M].北京:人民交通出版社,2004.
[2]PETTY K F,BICKEL P J,OSTLAND M,et al.Anew methodology for evaluating incident detection algorithms[J].Transportation Research Part C:Emerging Technologies,2002,10(3):189-204.
[3]HAWAS,YASER E.A Fozzy-based system for incident detection in urban street networks[J].Transportation Research Part C:Emerging Technologies,2007,15(2):69-95.
[4]WANG Y B,PAPAGEORGIOU M.Real-time freeway traffic state estimation based on extended kalman filter:ageneral approach[J].Transportation Research Part B,2005(1):141-167.
[5]巫威眺,靳文舟,林培群.基于BP神经网络的道路交通状态判别方法研究[J].交通信息与安全,2011,29(4):71-74.
[6]于荣,王国祥,郑继媛,等.基于支持向量机的城市道路交通状态模式识别研究[J].交通运输系统工程与信息,2013,13(1):130-136.
[7]张晓燕,宋国华,朱琳,等.基于FCD的城市路网常发性拥堵路段识别方法研究[J].交通信息与安全,2014,32(1):5-9.
[8]李佳,严余松.基于图像的交通拥堵状态识别系统的实现[J].计算机工程与设计,2011,32(4):1366-1369.
[9]叶卿.信号控制交叉口交通拥堵状态识别方法研究[D].广州:华南理工大学,2015.
[2]PETTY K F,BICKEL P J,OSTLAND M,et al.Anew methodology for evaluating incident detection algorithms[J].Transportation Research Part C:Emerging Technologies,2002,10(3):189-204.
[3]HAWAS,YASER E.A Fozzy-based system for incident detection in urban street networks[J].Transportation Research Part C:Emerging Technologies,2007,15(2):69-95.
[4]WANG Y B,PAPAGEORGIOU M.Real-time freeway traffic state estimation based on extended kalman filter:ageneral approach[J].Transportation Research Part B,2005(1):141-167.
[5]巫威眺,靳文舟,林培群.基于BP神经网络的道路交通状态判别方法研究[J].交通信息与安全,2011,29(4):71-74.
[6]于荣,王国祥,郑继媛,等.基于支持向量机的城市道路交通状态模式识别研究[J].交通运输系统工程与信息,2013,13(1):130-136.
[7]张晓燕,宋国华,朱琳,等.基于FCD的城市路网常发性拥堵路段识别方法研究[J].交通信息与安全,2014,32(1):5-9.
[8]李佳,严余松.基于图像的交通拥堵状态识别系统的实现[J].计算机工程与设计,2011,32(4):1366-1369.
[9]叶卿.信号控制交叉口交通拥堵状态识别方法研究[D].广州:华南理工大学,2015.