基于浮动车的道路交通状况评估中信息融合应用研究
|
摘要
智能交通系统(ITS)作为一个信息化的系统,它的各个组成部分和各种功能都是以交通信息应用为中心展开的,交通信息的质量直接影响着交通系统应用分析的可靠程度。因此,获取实时、全面、准确的道路交通信息是实现城市交通智能化的关键,也是ITS成功实施的重要前提和基本保障。本文以交通信息采集为应用背景,针对目前城市道路交通信息难以实现实时全面准确采集的问题,从信息融合的角度,对交通信息融合、交通信息预测以及FCD算法等问题进行了系统的研究。
全文的主要工作包括以下几个方面:
1.信息融合技术的理论基础研究,从系统的角度对信息融合技术的基础理论进行了研究,重点研究了信息融合技术作为一种系统思维方式的理论知识,这些知识是构成信息融合技术的基础。其主要内容包括信息融合的融合层次、功能模型以及数学模型。
2.基于FCD的城市道路交通信息采集研究。首先,提出了采样周期优化的理论方法,将浮动车瞬时速度当作随机信号,利用傅立叶变换对其进行频域分析,然后依据Shannon采样定理,确定浮动车的优化采样频率;重点讨论了在GPS返回数据的不同情况下,进行平均速度的估计。通过试验,说明该算法能够得到路段合理的平均速度,能够描述路网的运行状态。
3.由于固定检测器和移动检测器在检测覆盖范围方面存在较大差异,具有很强的互补性。在分析了固定检测器与移动检测器进行信息融合的必要性后,提出了基于交叉口分离的交通信息融合的总体框架。分别阐述了基于固定检测器和基于移动检测器的区间平均速度估计方法。
4.利用粗糙集理论的属性约简、值约简、核和不完备信息系统等方法来进行多传感器信息的融合,除了传感器测量的数据之外,无需任何额外的信息。针对完备信息系统和不完备信息系统分别提出了相应的融合算法,为解决传感器数据不完整的信息融合提供了有效的方法。
Intelligent transportation system (ITS) is an information-based system, where each sub-system and its function attach most importance to the application of traffic information. As a result, the validity of ITS depends highly on the quality of traffic information. To collect real-time, all-around, and accurate traffic information is the key of making urban transportation intellectualized and the important premise of implementing of ITS successfully. This dissertation makes researches on the information fusion of urban traffic information. Several related research works, such as FCD (Floating Car Data) algorithm and traffic information prediction etc., have been studied in this dissertation as well.
The main works in the thesis are introduced as follows.
1. To study the basic theory of information fusion technology. From a point of view, the hierarchy, the functional model, the structural model and the mathematical model of information fusion are discussed respectively.
2. To study the traffic information collection method based on FCD. Firstly presented a theoretical method for floating-car sampling cycle optimization: regarding speed as a stochastic signal, analyzed its frequency spectrum using Fourier transform, and decided the optimal sampling frequency by Shannon sampling theory, then this paper discusses the estimation algorithm of vehicle mean speed based on GPS data, especially under different conditions of the data according to the communication. The experiment shows the algorithm is reasonable.
3. Fixed detectors and mobile detectors are different at coverage area. They are complementary. The necessity of data fusion for fixed detectors and floating cars was analyzed. The architecture of traffic data fusion was proposed, which wad on the basis of discussing average speed calculating models based on fixed detectors and floating cars.
4. Using Rough Set theory to syncretize multi-sensor information rooted in property reduction, value reduction, and nucleus and incomplete information system etc. According to complete information system and incomplete information system, the corresponding amalgamation algorithms are shown, which provide an effective method to deal with overloading data of sensors and information amalgamation for incomplete sensor.
全文的主要工作包括以下几个方面:
1.信息融合技术的理论基础研究,从系统的角度对信息融合技术的基础理论进行了研究,重点研究了信息融合技术作为一种系统思维方式的理论知识,这些知识是构成信息融合技术的基础。其主要内容包括信息融合的融合层次、功能模型以及数学模型。
2.基于FCD的城市道路交通信息采集研究。首先,提出了采样周期优化的理论方法,将浮动车瞬时速度当作随机信号,利用傅立叶变换对其进行频域分析,然后依据Shannon采样定理,确定浮动车的优化采样频率;重点讨论了在GPS返回数据的不同情况下,进行平均速度的估计。通过试验,说明该算法能够得到路段合理的平均速度,能够描述路网的运行状态。
3.由于固定检测器和移动检测器在检测覆盖范围方面存在较大差异,具有很强的互补性。在分析了固定检测器与移动检测器进行信息融合的必要性后,提出了基于交叉口分离的交通信息融合的总体框架。分别阐述了基于固定检测器和基于移动检测器的区间平均速度估计方法。
4.利用粗糙集理论的属性约简、值约简、核和不完备信息系统等方法来进行多传感器信息的融合,除了传感器测量的数据之外,无需任何额外的信息。针对完备信息系统和不完备信息系统分别提出了相应的融合算法,为解决传感器数据不完整的信息融合提供了有效的方法。
Intelligent transportation system (ITS) is an information-based system, where each sub-system and its function attach most importance to the application of traffic information. As a result, the validity of ITS depends highly on the quality of traffic information. To collect real-time, all-around, and accurate traffic information is the key of making urban transportation intellectualized and the important premise of implementing of ITS successfully. This dissertation makes researches on the information fusion of urban traffic information. Several related research works, such as FCD (Floating Car Data) algorithm and traffic information prediction etc., have been studied in this dissertation as well.
The main works in the thesis are introduced as follows.
1. To study the basic theory of information fusion technology. From a point of view, the hierarchy, the functional model, the structural model and the mathematical model of information fusion are discussed respectively.
2. To study the traffic information collection method based on FCD. Firstly presented a theoretical method for floating-car sampling cycle optimization: regarding speed as a stochastic signal, analyzed its frequency spectrum using Fourier transform, and decided the optimal sampling frequency by Shannon sampling theory, then this paper discusses the estimation algorithm of vehicle mean speed based on GPS data, especially under different conditions of the data according to the communication. The experiment shows the algorithm is reasonable.
3. Fixed detectors and mobile detectors are different at coverage area. They are complementary. The necessity of data fusion for fixed detectors and floating cars was analyzed. The architecture of traffic data fusion was proposed, which wad on the basis of discussing average speed calculating models based on fixed detectors and floating cars.
4. Using Rough Set theory to syncretize multi-sensor information rooted in property reduction, value reduction, and nucleus and incomplete information system etc. According to complete information system and incomplete information system, the corresponding amalgamation algorithms are shown, which provide an effective method to deal with overloading data of sensors and information amalgamation for incomplete sensor.
引文
[1]张静,蔡伯根,吴建平.移动检测技术的研究[J].北方交通大学学报,2003,27(3):80.83.
[2]任江涛,张毅,许俊华.美欧日ITS体系结构比较分析[J].公路交通科技2001,18(2):61-65
[3]陆化普.智能运输系统[M].北京.人民交通出版社.2002
[4]National ITS Architecture,version 3.0
[5]张智文,魏凤,侯福深.中国智能运输系统(ITS)的发展[J].交通运输系统工程与信息2001(1):18-22
[6]史其信,陆化普.中国ITS发展战略构想[J].公路交通科技 1998 15(3):13-16
[7]E.L.Waltz and D.M.Buede,Data Fusion and Decision Support for Command and Control[J].IEEE Trans.Syst.,Man Cybem.1986,16(6):865-879
[8]D.L.Hall and J.Llinas,An Introduction to Multisensor Data Fusion,Proceedings of the IEEE,1997,85(1):6-23
[9]B.V.Dasarathy,Sensor Fusion Potential Exploitation-innovative Architectures and Illustrative Applications,Proceedings of the IEEE,1997,85(1):24-38
[10]S.D.E.Elisa and P.L.Blodgett,The Extended OODA Model for Data Fusion Systems,Proc.of 2001 International Conference on Information Fusion,Canada,2001:106-112
[11]B.Mark and O.B.J.Jane,Tire Omnibus Model:A New Model of Data Fusion,Proc.of 1999International Conference on Information Fusion,California,USA,1999:337-345
[12]刘叶玲,朱艳伟.加权数据融合算法及其应用举例[J].西安科技大学学报,2005,25(2):253-255
[13]盛骤,谢式千,潘承毅.概率论与数理统计[M].北京:高等教育出版社.1989
[14]Han Jiawei,Micheline K.数据挖掘概念与技术[M].范明,孟小峰译.北京:机械工业出版社,2001
[15]PAWLAK Z.Rough sets-theoretical aspects of reasoning about data[M].Dordrecht:Kluwer Academic Publications,1991
[16]张文修.粗糙集理论与方法[M],北京:科学出版社,2001
[17]孙晓峰,吴建平.基于浮动车数据采集技术的城市交通网络功能评价方法研究[J].现代交通技术 2005.(6).55-58
[18]Boyce D,Kirson A.Schofer J.Design and Implementation of ADVANCE[A].IEEE Proceeding of 3rd Inter.Conf.on Vehicle Navigation and Information Systems[C].Ottawa.1993.415-426
[19]Karl Frazier Petty.Incidents on the Freeway:Detection and Management[D].Berkeley:University of California.1997.
[20]F.W.Cathey.& D.J.Dailey.Transit Vehicles as Traffic Probe Sensors[A].IEEE Intelligent Transportation Systems Conference Proceedings.Oakland[C].USA.August.2001,579-584.
[21]Chung E.Sarvi M.Murakami Y.Horiguchi.R.Kuwahara M.Cleansing of probe car data to determine trip OD.[EB/OL].2001.5.8.
[22]王文佳.交通探测车系统的发展前景和需要解决的问题[J].产业与市场.No.6,2005,90-92.
[23]王力,王川久,范耀祖等.智能交通系统中动态交通信息采集新方法研究[J],系统工程.Vol.23(2),No.2.2005.86-89.
[24]Wang Li,Chuanjiu Wang,Yuexu Fan.et al.Probe vehicle sampling for real-time traffic data collection[A].IEEE Proceeding of Intelligent Transportation Systems[C].13-16,Sept.2005:886-888
[25]路加.交通拥挤的度量方法与基于浮动车的交通拥挤检测[D].北京:清华大学,2003.12.
[26]国家its工程技术研究中心城市交通部.我中心申报的2005年科研院所技术开发研究专项资金项目获科技部立项批复.[EB/OL].http://www.itsc.com.cn/ViewNews.asp?ID=7479.2005.8.25.
[27]Quiroga.C.A.& Bullock.D.(1998)Determination of sample size for travel time studies[J].ITE Journal.68(8).92-98.
[28]Chen.M.& Chien.S.I.J(2000)Determining the number of probe.vehicles for freeway travel time estimation using microscopic simulation[A].Transportation Research Board 79th Annual Meeting[C].No.00-1334 TRB Washington.D.C.
[29]Srinivasan.K.& Jovanis.P.(1996).Determination of the number of probe vehicles required for reliable travel time measurement in an urban network[J].Transportation Research Record 1537.TRB Washington.D.C.15-22.
[30]Xiaowen Dai,Martin A,Ferman,Rohert P,Roessero A Simulation Evaluation of a Real-Time Traffic Information System Using Probe Vehicles[A].IEEE Proc.of Intelligent Transportation Systems[C].Volume:1.12-15 Oct.2003.475-480.
[31]Ruey Long Cheu.Chi Xi and Der-Hong Lee.Probe Vehicle Population and Sample Size for Arterial Speed Estimation[J].Computer-Aided Civil and Infrastructure Engineering.17.2002.53-60.
[32]Chris Dranee.Jean-Lue Ygnace.Cellular telecommunication and transportation convergence,a case study of a research conducted in California and in France on cellular positioning techniques and transportation issue[A].2001 IEEE Intelligent transportation systems conference proceedings[C].Oakland.2001.16-22.
[33]Fushiki T.Traffic Condition Prediction by Use of Floating Car[J].IPSJ Journal,2002,43(12):3801-3808.
[34]万宇.基于GPS定位的浮动车样本数量确定方法研究[J].交通与安全,2002.No.156
[35]王炜,过秀成.交通工程学[M].南京:东南大学出版社,2000:127;82-107.
[36]翁剑成,荣建,于泉,任福田.基于浮动车数据的行程速度估计算法及优化[J].北京工业大学学报,2007,33(5):460-464
[37]李春杰.高速公路车辆检测器的综合比选[J].中国交通信息产业,2006.(2).98-104.
[38]常犁云,王国胤,吴渝.一种Rough Set理沦的属性约简及规则提取方法[J].软件学报.1999.10(11):1206-1211
[39]王珏,苗夺谦,周育健.关于Rough Set理论与应用的综述[J].模式识别与人工智能.1994.9(4):337-344
[40]王志海,胡可云,胡学钢等.基于粗糙集合理论的知识发现综述[J].模式识别与人工智能,1993.11(21:176-183
[41]Wang G Y,Liu F.The Inconsistency in Rough Set Based Rule Generation[A].The Second International Conference on Rough Sets and Current Trends in Computing,2000,332-339
[42]方世昌.离散数学.西安:西安电子科技大学出版社.1989
[43]袁晶矜,袁振洲.信号交叉口通行能力计算方法的比较分析[J].公路交通技.2006.No.5
[44]沙云飞,曹瑾鑫.基于GPS的路段旅行时问和速度估计算法研究[J].ITS通讯.46-48
[2]任江涛,张毅,许俊华.美欧日ITS体系结构比较分析[J].公路交通科技2001,18(2):61-65
[3]陆化普.智能运输系统[M].北京.人民交通出版社.2002
[4]National ITS Architecture,version 3.0
[5]张智文,魏凤,侯福深.中国智能运输系统(ITS)的发展[J].交通运输系统工程与信息2001(1):18-22
[6]史其信,陆化普.中国ITS发展战略构想[J].公路交通科技 1998 15(3):13-16
[7]E.L.Waltz and D.M.Buede,Data Fusion and Decision Support for Command and Control[J].IEEE Trans.Syst.,Man Cybem.1986,16(6):865-879
[8]D.L.Hall and J.Llinas,An Introduction to Multisensor Data Fusion,Proceedings of the IEEE,1997,85(1):6-23
[9]B.V.Dasarathy,Sensor Fusion Potential Exploitation-innovative Architectures and Illustrative Applications,Proceedings of the IEEE,1997,85(1):24-38
[10]S.D.E.Elisa and P.L.Blodgett,The Extended OODA Model for Data Fusion Systems,Proc.of 2001 International Conference on Information Fusion,Canada,2001:106-112
[11]B.Mark and O.B.J.Jane,Tire Omnibus Model:A New Model of Data Fusion,Proc.of 1999International Conference on Information Fusion,California,USA,1999:337-345
[12]刘叶玲,朱艳伟.加权数据融合算法及其应用举例[J].西安科技大学学报,2005,25(2):253-255
[13]盛骤,谢式千,潘承毅.概率论与数理统计[M].北京:高等教育出版社.1989
[14]Han Jiawei,Micheline K.数据挖掘概念与技术[M].范明,孟小峰译.北京:机械工业出版社,2001
[15]PAWLAK Z.Rough sets-theoretical aspects of reasoning about data[M].Dordrecht:Kluwer Academic Publications,1991
[16]张文修.粗糙集理论与方法[M],北京:科学出版社,2001
[17]孙晓峰,吴建平.基于浮动车数据采集技术的城市交通网络功能评价方法研究[J].现代交通技术 2005.(6).55-58
[18]Boyce D,Kirson A.Schofer J.Design and Implementation of ADVANCE[A].IEEE Proceeding of 3rd Inter.Conf.on Vehicle Navigation and Information Systems[C].Ottawa.1993.415-426
[19]Karl Frazier Petty.Incidents on the Freeway:Detection and Management[D].Berkeley:University of California.1997.
[20]F.W.Cathey.& D.J.Dailey.Transit Vehicles as Traffic Probe Sensors[A].IEEE Intelligent Transportation Systems Conference Proceedings.Oakland[C].USA.August.2001,579-584.
[21]Chung E.Sarvi M.Murakami Y.Horiguchi.R.Kuwahara M.Cleansing of probe car data to determine trip OD.[EB/OL].2001.5.8.
[22]王文佳.交通探测车系统的发展前景和需要解决的问题[J].产业与市场.No.6,2005,90-92.
[23]王力,王川久,范耀祖等.智能交通系统中动态交通信息采集新方法研究[J],系统工程.Vol.23(2),No.2.2005.86-89.
[24]Wang Li,Chuanjiu Wang,Yuexu Fan.et al.Probe vehicle sampling for real-time traffic data collection[A].IEEE Proceeding of Intelligent Transportation Systems[C].13-16,Sept.2005:886-888
[25]路加.交通拥挤的度量方法与基于浮动车的交通拥挤检测[D].北京:清华大学,2003.12.
[26]国家its工程技术研究中心城市交通部.我中心申报的2005年科研院所技术开发研究专项资金项目获科技部立项批复.[EB/OL].http://www.itsc.com.cn/ViewNews.asp?ID=7479.2005.8.25.
[27]Quiroga.C.A.& Bullock.D.(1998)Determination of sample size for travel time studies[J].ITE Journal.68(8).92-98.
[28]Chen.M.& Chien.S.I.J(2000)Determining the number of probe.vehicles for freeway travel time estimation using microscopic simulation[A].Transportation Research Board 79th Annual Meeting[C].No.00-1334 TRB Washington.D.C.
[29]Srinivasan.K.& Jovanis.P.(1996).Determination of the number of probe vehicles required for reliable travel time measurement in an urban network[J].Transportation Research Record 1537.TRB Washington.D.C.15-22.
[30]Xiaowen Dai,Martin A,Ferman,Rohert P,Roessero A Simulation Evaluation of a Real-Time Traffic Information System Using Probe Vehicles[A].IEEE Proc.of Intelligent Transportation Systems[C].Volume:1.12-15 Oct.2003.475-480.
[31]Ruey Long Cheu.Chi Xi and Der-Hong Lee.Probe Vehicle Population and Sample Size for Arterial Speed Estimation[J].Computer-Aided Civil and Infrastructure Engineering.17.2002.53-60.
[32]Chris Dranee.Jean-Lue Ygnace.Cellular telecommunication and transportation convergence,a case study of a research conducted in California and in France on cellular positioning techniques and transportation issue[A].2001 IEEE Intelligent transportation systems conference proceedings[C].Oakland.2001.16-22.
[33]Fushiki T.Traffic Condition Prediction by Use of Floating Car[J].IPSJ Journal,2002,43(12):3801-3808.
[34]万宇.基于GPS定位的浮动车样本数量确定方法研究[J].交通与安全,2002.No.156
[35]王炜,过秀成.交通工程学[M].南京:东南大学出版社,2000:127;82-107.
[36]翁剑成,荣建,于泉,任福田.基于浮动车数据的行程速度估计算法及优化[J].北京工业大学学报,2007,33(5):460-464
[37]李春杰.高速公路车辆检测器的综合比选[J].中国交通信息产业,2006.(2).98-104.
[38]常犁云,王国胤,吴渝.一种Rough Set理沦的属性约简及规则提取方法[J].软件学报.1999.10(11):1206-1211
[39]王珏,苗夺谦,周育健.关于Rough Set理论与应用的综述[J].模式识别与人工智能.1994.9(4):337-344
[40]王志海,胡可云,胡学钢等.基于粗糙集合理论的知识发现综述[J].模式识别与人工智能,1993.11(21:176-183
[41]Wang G Y,Liu F.The Inconsistency in Rough Set Based Rule Generation[A].The Second International Conference on Rough Sets and Current Trends in Computing,2000,332-339
[42]方世昌.离散数学.西安:西安电子科技大学出版社.1989
[43]袁晶矜,袁振洲.信号交叉口通行能力计算方法的比较分析[J].公路交通技.2006.No.5
[44]沙云飞,曹瑾鑫.基于GPS的路段旅行时问和速度估计算法研究[J].ITS通讯.46-48