吉林大学学报(工学版) ›› 2015, Vol. 45 ›› Issue (1): 97-103.doi: 10.13229/j.cnki.jdxbgxb201501015

• 论文 • 上一篇    下一篇

面向城市道路的地磁传感器单节点车型分类

李海舰1，董宏辉1，史元超2，贾利民1，郭卫锋3   

  1. 1.北京交通大学 轨道交通控制与安全国家重点实验室， 北京 100044；
    2.中铁国际多式联运有限公司， 北京 100161；
    3.西昌卫星发射中心， 四川 西昌 571339
  • 收稿日期:2013-05-27 出版日期:2015-02-01 发布日期:2015-02-01
  • 通讯作者: 贾利民(1963),男,教授,博士生导师.研究方向:智能运输系统.E-mail:jialm@vip.sina.com
  • 作者简介:李海舰(1986)，男，博士研究生.研究方向:智能交通系统，交通传感器网络.E-mail:lihaijian0506@163.com
  • 基金资助:
    “863”国家高技术研究发展计划项目(2012AA112401,2011AA110505)；国家自然科学基金项目(61104164).

Vehicle classification with a single magnetic sensor for urban road

LI Hai-jian1,DONG Hong-hui1,SHI Yuan-chao2,JIA Li-min1,GUO Wei-feng3   

  1. 1.State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China;
    2. China Railway International Multimodal Transport Co.,Ltd, Beijing 100161, China;
    3.Xichang Satellite Launch Center, Xichang 571339, China
  • Received:2013-05-27 Online:2015-02-01 Published:2015-02-01

RICH HTML

0   

PDF (PC)

339

摘要： 提出了一种利用多功能地磁传感器采集道路环境磁场数据，并基于决策树模型实现车型的在线分类方法。文中提取8种与车速无关的车辆波形时域特征作为模型输入，基于最优最小划分样本数的CART算法对决策树模型进行训练。对训练得到的决策树，基于最小误差剪枝原则进行剪枝，得到具有更高样本鲁棒性的最佳剪枝树。通过在北京市某道路上布设地磁传感器获取了两种车型数据，正、反向测试的平均准确率分别为88.9%和94.4%。与现有多个分类方法进行了对比实验，结果表明:本文方法能够进行在线车型分类，并在分类准确率、样本鲁棒性和算法执行时间等方面更具优势，能够应用于实际城市道路现场进行车型分类。

关键词: 道路工程, 车型分类, 地磁传感器, CART算法, 决策树

Abstract: An online vehicle classification method based on decision tree model is proposed, in which multi-functional magnetic sensors are used to collect field magnetic data. First, eight speed-independent time-domain waveform features are extracted as the inputs of the decision tree model. Then the decision tree model is trained based on the Classification and Regression Tree (CART) algorithm with the Minimum Number of Slit-samples (MNS). Finally the trained decision tree model is pruned with a Minimum Error Pruning (MEP) role to obtain an optimal pruning tree, which is more robust to new samples. For the field samples collected from a road in Beijing with two types of vehicles, the average classification accuracies of the forward and reverse tests are 88.9% and 94.4% respectively. The proposed classification method is compared with existing methods. The results show that the proposed method enables online vehicle type classification with the advantages of high classification accuracy, sample robustness and less algorithm execution time.

Key words: road engineering, vehicle classification, magnetic sensor, CART algorithm, decision tree

中图分类号: 

  • U491
[1] Cheung S Y, Varaiya P. Traffic surveillance by wireless sensor networks: final report[R]. California: University of California, Berkeley,2007.
[2] Kafai M, Bhanu B. Dynamic bayesian networks for vehicle classifcation in video[J]. IEEE Transactions on Industrial Informatics,2012,20(1):100-109.
[3] Rajesh P, Geetha M K, Ramu R. Traffic density estimation, vehicle classification and stopped vehicle detection for traffic surveillance system using predefined traffic videos[J]. Computer Science and Engineering,2013,56:13671-13676.
[4] Guo B F, Nixon M S, Damarla T R. Acoustic information fusion for ground vehicle classifcation[C]∥The 11th International Conference on Information Fusion,Cologne: Institute of Electrical and Electronics Engineers Inc,2008:1-7.

[5] Paulraj M P, Adoma A H, Sundararaj S, et al. A. Moving vehicle recognition and classification based on time domain approach[J]. Procedia Engineering,2013,53:405-410.
[6] 陈强,李江,王双维,等.基于AR模型的车型自动分类技术[J].吉林大学学报:工学版,2007,37(2):325-328.
Chen Qiang, Li Jiang, Wang Shuang-wei, et al. Automatic vehicle classification by radiated noise of vehicles based on AR model[J]. Journal of Jilin University (Engineering and Technology Edition),2007,37(2):325-328.
[7] Jeng S T, Chu L, Hernandez S V. A wavelet-KNN based vehicle classification approach using inductive loop signatures[C]∥Transportation Research Board 92nd Annual Meeting,Washington: Transportation Research Board,2013.
[8] Coifman B, Kimb S. Speed estimation and length based vehicle classication from freeway single-loop detectors[J]. Transportation Research Part C,2009,17(4):349-364.
[9] Kaewkamnerd S, Pongthornseri R, Chinrungrueng J, et al. Automatic vehicle classification using wireless magnetic sensor[C]∥IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications,Rende: Institute of Electrical and Electronics Engineers Inc,2009:420-424.
[10] 杨兆升,杨志宏,赵丹华.高速公路收费系统的车型自动分类[J].吉林大学学报:工学版,2002,32(3): 6-9.
Yang Zhao-sheng, Yang Zhi-hong, Zhao Dan-hua. Research on vehicle auto classification of freeway toll collection system[J]. Journal of Jilin University (Engineering and Technology Edition),2002,32(3):6-9.
[11] Li Hai-jian, Dong Hong-hui, Jia Li-min, et al. Some practical vehicle speed estimation methods by a single traffic magnetic sensor[C]∥The 14th International IEEE Conference on Intelligent Transportation Systems,Washington: Institute of Electrical and Electronics Engineers Inc,2011:1566-1573.
[12] Wu Xin-dong, Kumar V. CART: Classication and Regression Trees[M]. London:Chapman and Hall/CRC,2009:179-207.
[13] Quinlan J R. Induction of decision trees[J]. Machine Learning,1986,1(1):81-106.
[1] 李伊,刘黎萍,孙立军. 沥青面层不同深度车辙等效温度预估模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1703-1711.
[2] 臧国帅, 孙立军. 基于惰性弯沉点的刚性下卧层深度设置方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1037-1044.
[3] 念腾飞, 李萍, 林梅. 冻融循环下沥青特征官能团含量与流变参数灰熵分析及微观形貌[J]. 吉林大学学报(工学版), 2018, 48(4): 1045-1054.
[4] 宫亚峰, 申杨凡, 谭国金, 韩春鹏, 何钰龙. 不同孔隙率下纤维土无侧限抗压强度[J]. 吉林大学学报(工学版), 2018, 48(3): 712-719.
[5] 程永春, 毕海鹏, 马桂荣, 宫亚峰, 田振宏, 吕泽华, 徐志枢. 纳米TiO2/CaCO3-玄武岩纤维复合改性沥青的路用性能[J]. 吉林大学学报(工学版), 2018, 48(2): 460-465.
[6] 张仰鹏, 魏海斌, 贾江坤, 陈昭. 季冻区组合冷阻层应用表现的数值评价[J]. 吉林大学学报(工学版), 2018, 48(1): 121-126.
[7] 季文玉, 李旺旺, 过民龙, 王珏. 预应力RPC-NC叠合梁挠度试验及计算方法[J]. 吉林大学学报(工学版), 2018, 48(1): 129-136.
[8] 马晔, 尼颖升, 徐栋, 刁波. 基于空间网格模型分析的体外预应力加固[J]. 吉林大学学报(工学版), 2018, 48(1): 137-147.
[9] 罗蓉, 曾哲, 张德润, 冯光乐, 董华均. 基于插板法膜压力模型的沥青混合料水稳定性评价[J]. 吉林大学学报(工学版), 2017, 47(6): 1753-1759.
[10] 尼颖升, 马晔, 徐栋, 李金凯. 波纹钢腹板斜拉桥剪力滞效应空间网格分析方法[J]. 吉林大学学报(工学版), 2017, 47(5): 1453-1464.
[11] 郑传峰, 马壮, 郭学东, 张婷, 吕丹, 秦泳. 矿粉宏细观特征耦合对沥青胶浆低温性能的影响[J]. 吉林大学学报(工学版), 2017, 47(5): 1465-1471.
[12] 于天来, 郑彬双, 李海生, 唐泽睿, 赵云鹏. 钢塑复合筋带挡土墙病害及成因[J]. 吉林大学学报(工学版), 2017, 47(4): 1082-1093.
[13] 蔡氧, 付伟, 陶泽峰, 陈康为. 基于扩展有限元模型的土工布防荷载型反射裂缝影响分析[J]. 吉林大学学报(工学版), 2017, 47(3): 765-770.
[14] 刘寒冰, 张互助, 王静. 失水干燥对路基压实黏质土抗剪强度特性的影响[J]. 吉林大学学报(工学版), 2017, 47(2): 446-451.
[15] 崔亚楠, 韩吉伟, 冯蕾, 李嘉迪, 王乐. 盐冻循环条件下改性沥青微细观结构[J]. 吉林大学学报(工学版), 2017, 47(2): 452-458.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发