基于支持向量机的城市道路交通状态模式识别研究

交通运输系统工程与信息 ›› 2013, Vol. 13 ›› Issue (1): 130-.

基于支持向量机的城市道路交通状态模式识别研究

于荣¹，王国祥¹，郑继媛^2,3，王海燕^*2

1.南京财经大学管理科学与工程学院，南京 210046； 2.江苏省质量安全工程研究院，南京 210046； 3.东南大学交通学院，南京210002

收稿日期:2012-09-25 修回日期:2012-11-09 出版日期:2013-02-25 发布日期:2013-03-04
作者简介:于荣（1985-），女，江苏东海人，讲师，博士.
基金资助:
美国能源基金会资助项目（G-1208-16658）.

Urban Road Traffic Condition Pattern Recognition Based on Support Vector Machine

YU Rong¹, WANG Guo-xiang¹, ZHENG Ji-yuan^2,3，WANG Hai-yan²

1. School of Management Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210046, China; 2. Jiangsu Province Institute of Quality and Safety Engineering, Nanjing 210046, China; 3. School of Transportation, Southeast University, Nanjing 210002, China

Received:2012-09-25 Revised:2012-11-09 Online:2013-02-25 Published:2013-03-04

摘要/Abstract

摘要：

城市道路交通状态识别是现代智能交通系统的重要组成部分，是交通智能控制、诱导和协同系统的基础.基于支持向量机建立车流量、平均速度和占有率的三维反映空间，以堵塞流、拥挤流、平稳流和顺畅流为标签对道路交通状态进行分类；并在MATLAB平台下利用LiBSVM工具包进行实验分析，对SVM各种核函数的分类效果进行比较研究，实现了支持向量机技术的交通状态模式识别.结果表明：选择的指标能很好地反映交通状态的特征，SVM核函数可以以较高的分类精度区分开交通流的状态识别，数据的归一化对分类的结果具有重要的影响.

关键词: 城市道路交通, 交通状态, 模式识别, 支持向量机, LiBSVM

Abstract:

As an important part of the modern intelligent transportation system, urban transport condition recognition is the base of intelligent control, guidance and synergy system. This paper establishes a three-dimensional space with traffic volume, average speed and occupation ratio. It then classifies transportation condition patterns in terms of blocking flow, crowded flow, steady flow and unhindered flow based on wide literature review. Furthermore, this paper presents the algorithm with the MATALB LiBSVM toolbox. To process the data, this paper compares the classification result of different SVM kernel functions and thus realizes the transport condition pattern recognition via the support vector machine (SVM). The results reveal that the selected indexes effectively reflect the characteristics of the traffic conditions. The SVM kernel function can separate different patterns from traffic flows with high classification accuracy, and the data normalization has a significant influence on the result of classification.

Key words: urban road traffic, traffic state, pattern recognition, support vector machine (SVM), LiBSVM

中图分类号:

U491

于荣，王国祥，郑继媛，王海燕. 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-.

YU Rong, WANG Guo-xiang, ZHENG Ji-yuan，WANG Hai-yan. Urban Road Traffic Condition Pattern Recognition Based on Support Vector Machine[J]. Journal of Transportation Systems Engineering and Information Technology, 2013, 13(1): 130-.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract18533.shtml

http://www.tseit.org.cn/CN/Y2013/V13/I1/130

参考文献

[1] 皮晓亮，杨晓光，孙亚．基于环形线圈检测器采集信息的交通状态分类方法应用研究[J]．华东公路，2006(1)：33-38．[PI X L，YANG X G，SUN Y．Application research of traffic state classification method based on collected Information from loop detector[J]．East China Highway，2006(1) ：33-38．]

[2] Adel W Sadek ，Michael J Demetsky ，Brain L Smith．Casebased reasoning for real time traffic flow management[J]． ComputerAided Civil and Infrastructure Engineering，1999，14:347-356．

[3] Francesco Palmieri，Ugo Fiore．A nonlinear recurrencebased approach to traffic classification [J]．Computer Networks ，2009,53(6):761-773.

[4] Angélica Lozano，Giuseppe Manfredi，Luciano Nieddu．An algorithm for the recognition of levels of congestion in road traffic problems [J]．Matherematics and computers in simulation，2009，76(6)：1926-1934．

[5] M.MontazeriGh，A Fotouhi. Traffic condition recognition using the k-means clustering method [J]． Transportation Research B: Mechanical Engineering，2011，18 (4)：930-937.

[6] Mohamed AbdelAty，Anurag Pande．Identifying crash propensity using specific traffic speed conditions [J]．Journal of Safety Research， 2005，36(1)：91-108．

[7] Andrzej Ruta，Yongmin Li， Xiaohui Liu．Realtime traffic sign recognition from video by classspecific discriminative features [J]． Pattern Recognition，2010，43（1)：416-430．

[8] 美国交通研究委员会．道路通行能力手册[M]．人民交通出版社，2007．[U S Transportation Research Board．Highway capacity manual[M]．China Communications Press，2007.]

[9] 李清泉，高德荃，杨必胜．基于模糊支持向量机的城市道路交通状态分类[J]．吉林大学学报（工学版），2009，39：131-134．[LI Q Q，GAO D Q，YANG B S．Urban road traffic status classification based on fuzzy support vector machines[J]．Journal of Jilin University(Engineering and Technology Edition)，2009，39：131-134．]

[10] 李志恒，孙东，靳雪翔,等．基于模式的城市交通状态分类与性质研究[J]．交通运输系统工程与信息，2008，8(5)：83-87．[LI Z H，SUN D，JIN X X et, al．PatternBased study on urban transportation system states and properties with fuzzy reasoning methods[J]．Journal of Transportation Systems Engineering and Information Technology，2008，8(5)：83-87．]

[11] 任江涛，欧晓凌，张毅,等．交通状态模式识别研究[J]．公路交通科技，2003，20(2)：63-67．[REN J T，OU X L，ZHANG Y, et al．Pattern recognition of traffic states[J]．Journal of Highway and Transportation Research and Development，2003，20(2)：63-67．]

[12] Kannal L．Patterns in pattern recognition：1968-1974 [J]．IEEE Trans. on Information Theory，1974，20(6)．

[13] 李作敏．交通工程学[M]．人民交通出版社，2000．[LI Z M．Traffic engineering[M]．China Communications Press，2000．]

[14] 杨淑莹．模式识别与智能计算——MATLAB技术实现[M]．电子工业出版社，2011．[YANG S Y．Pattern recognition and intelligent computing——MATLAB technology realization[M]．Publishing House of Electronics Industry，2011．]

[15] JP Marques de Sá著，吴逸飞译．模式识别——原理方法及应用[M]．清华大学出版社，2002．[JP Marques de Sá，WU Y F．Pattern recognition——Principle，method and application[M]．Tsinghua University Press，2002．]

[16] 孙即祥．现代模式识别[M]．高等教育出版社，2008．[SUN J X．Modern pattern recognition[M]．Higher Education Press，2008．]

[17] Richard O Duda， Peter E Hart，David G Stork著，李宏东等译．模式分类[M]．电子工业出版社，2010．[Richard O Duda，Peter E Hart， David G Stork，LI H D. Pattern classification[M]. Publishing House of Electronics Industry，China CITIC Press，2010．]

[18] 张学工．模式识别（第三版）[M]．清华大学出版社，2010．[ZHANG X G． Pattern recognition(Third edition) [M]．Tsinghua University Press，2010．] [19] ChihWei Hsu， ChihChung Chang， ChihJen Lin． A practical guide to support vector classification[EB/OL]．http://www.csie.ntu.edu.tw/~cjlin．