基于支持向量机的道路地下空洞量化识别方法
|
摘要
如何实现地下空洞的量化识别是探地雷达技术在城市道路地下空洞探测应用中的难题。针对城市道路地下空洞识别具有的小样本、非线性及高维模式识别特征,本文提出了一种基于支持向量机(SVM)的地下空洞量化识别方法。首先进行地下空洞正演模拟,对地下空洞雷达模拟数据进行预处理并进行数据降维,然后对降维后的数据进行时间域特征提取,利用SVM算法进行分类训练并构建空洞识别模型,最后应用该模型实现对地下空洞测试数据的量化识别。应用该方法分别对城市道路地下空洞正演模拟数据和物理模型数据进行实验验证,结果表明:本方法可以实现城市道路地下空洞的量化识别,其中正演模拟数据空洞识别精确度达到94%,空洞大小误差为±0.1m;物理模型数据空洞识别精确度达到82%,空洞大小误差为±0.2m。本方法可应用在城市道路地下空洞的量化识别中,为道路安全提供技术支撑。
It is a difficult problem for quantitative identification of the underground cavities by using ground penetrating radar technique in urban road. Aiming at the small sample, nonlinear and high-dimensional pattern recognition features for urban road underground cavity identification, an underground cavity quantitative identification method is proposed based on support vector machine(SVM). Firstly, the forward simulation of underground cavity is performed and the forward simulation data is preprocessed and dimension-reduced, and time domain feature extraction is carried out on the reduced dimension data. Then the SVM algorithm is used for classification training and the cavity identification model is constructed, which is used for the application. The verification experiments are implemented for forward model data and physical model data by using this proposed method, and the results show that this method can realize the quantitative identification of underground cavities in urban roads, and the accuracy of cavities identification for forward simulation data reaches 94% with error at ±0.1 m, and the accuracy for physical model data reaches 82% with error at ±0.2 m. This method can be applied for the quantitative identification of road underground cavities, providing technical support for road safety.
It is a difficult problem for quantitative identification of the underground cavities by using ground penetrating radar technique in urban road. Aiming at the small sample, nonlinear and high-dimensional pattern recognition features for urban road underground cavity identification, an underground cavity quantitative identification method is proposed based on support vector machine(SVM). Firstly, the forward simulation of underground cavity is performed and the forward simulation data is preprocessed and dimension-reduced, and time domain feature extraction is carried out on the reduced dimension data. Then the SVM algorithm is used for classification training and the cavity identification model is constructed, which is used for the application. The verification experiments are implemented for forward model data and physical model data by using this proposed method, and the results show that this method can realize the quantitative identification of underground cavities in urban roads, and the accuracy of cavities identification for forward simulation data reaches 94% with error at ±0.1 m, and the accuracy for physical model data reaches 82% with error at ±0.2 m. This method can be applied for the quantitative identification of road underground cavities, providing technical support for road safety.
引文
[1] 彭苏萍, 杨峰, 许献磊. GPR城市道路病害检测应用技术研究综述[J]. 办公自动化, 2014,(S1): 134～139.Peng Suping, Yang Feng, Xu Xianlei. Research summary on GPR urban roads disease detection application technology[J]. Office Informatization, 2014,(S1): 134～139. (in Chinese)
[2] 赵晓博. 隧道管波对于地震反射波法超前地质预报影响分析[J]. 工程勘察, 2018,(11): 74～78.Zhao Xiaobo. Analysis of influence of tunnel tube wave on geological forecast of seismic reflection wave method[J]. Geotechnical Investigation & Surveying, 2018,(11): 74～78. (in Chinese)
[3] 张劲松, 王星杰, 王晓岩. 隧道衬砌病害雷达检测定位精度分析[J]. 工程勘察, 2018, 46(4): 53～56.Zhang Jinsong, Wang Xingjie, Wang Xiaoyan. Detection and location of tunnel lining disease with radar[J]. Geotechnical Investigation & Surveying, 2018, 46(4): 53～56. (in Chinese)
[4] 秦镇, 吴海波, 张恩泽. 探地雷达在城市交通建设中的技术应用[J]. 西部探矿工程, 2018, 30(4): 95～98,103.Qin Zhen, Wu Haibo, Zhang Enze. Application of ground penetrating radar in urban traffic construction[J]. West-china Exploration Engineering, 2018, 30(4): 95～98,103. (in Chinese)
[5] 项雷. 公路隧道检测中探地雷达图像自动解释算法研究[D]. 南昌:南昌大学, 2013.Xiang Lei. Research on automatic interpretation algorithm of GPR image in highway tunnel detection[D]. Nanchang: Nanchang University, 2013. (in Chinese)
[6] 王春和, 胡通海, 崔海涛等. 探地雷达技术用于地下空洞塌陷灾害普查探测的创新与实践 [J]. 测绘通报, 2013,(S2): 13～16.Wang Chunhe, Hu Tonghai, Cui Haitao et al. The innovation and practice of ground penetrating radar technology used for disasters investigation especially for underground cavity or collapse detection[J]. Bulletin of Surveying and Mapping, 2013,(S2): 13～16. (in Chinese)
[7] 陈运飞, 刘士海, 李东海. 基于探地雷达技术的道路检测探究及应用[J]. 市政技术, 2018, 36(1): 20～22.Chen Yunfei, Liu Shihai, Li Donghai. Research and application of road detection based on ground penetrating radar technology[J]. Municipal Engineering Technology, 2018, 36(1): 20～22. (in Chinese)
[8] 周钰邦, 钟邱平, 马俊杰. 道路旁侧地下通道的物探响应特征[J]. 西南公路, 2018,(1): 48～52.Zhou Yubang, Zhong Qiuping, Ma Junjie. Geophysical response characteristics of roadside underground tunnels[J]. Southwest Highway, 2018,(1): 48～52. (in Chinese)
[9] 蒋维东, 黄欢, 贾茜淳等. 地质雷达在地下暗渠探测中的应用[J]. 人民珠江, 2018, 39(3): 42～48.Jiang Weidong, Huang Huan, Jia Xichun et al. Application of ground penetrating radar in underground drainage culvert detection[J]. Pearl River, 2018, 39(3): 42～48. (in Chinese)
[10] Lakshmi G, Panicker JR, Meera M. Named entity recognition in malayalam using fuzzy support vector machine[A]. Proceedings of 2016 International Conference on Information Science (ICIS) Kochi[C]. Japan, 2016, 201～206.
[11] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273～297.
[12] 刘方园, 王水花, 张煜东. 支持向量机模型与应用综述[J]. 计算机系统应用, 2018, 27(4): 1～9.Liu Fangyuan, Wang Shuihua, Zhang Yudong. Overview on models and applications of support vector machine[J]. Computer Systems & Applications, 2018, 27(4): 1～9. (in Chinese)
[13] 邹华胜. 路基病害识别算法与应用研究[J]. 地球物理学进展, 2009, 24(6): 2302～2307.Zou Huasheng. A study on roadbed disease recognition algorithm and application[J]. Progress in Geophysics, 2009, 24(6): 2302～2307. (in Chinese)
[14] Ryu J, Koo HI, Cho NI. Word segmentation method for handwritten documents based on structured learning[J]. IEEE Signal Processing Letters, 2015, 22(8): 1161～1165.
[15] Zhang ZM, Torr PHS. Object proposal generation using two-stage cascade SVMs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 102～115.
[16] Bo CJ, Lu HC and Wang D. Hyperspectral image classification via JCR and SVM models with decision fusion[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(2): 177～181.
[17] 张华美. 穿墙雷达基于支持向量机的成像算法研究[D]. 南京:南京邮电大学, 2015.Zhang Huamei. Study on imaging algorithm based on support vector machines for through-the-wall radars[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2015. (in Chinese)
[18] 周辉林, 姜玉玲, 徐立红等. 基于SVM的高速公路路基病害自动检测算法[J]. 中国公路学报, 2013, 26(2): 42～47.Zhou Huilin, Jiang Yuling, Xu Lihong et al. Automatic detection algorithm for expressway subgrade diseases based on SVM[J]. China Journal of Highway and Transport, 2013, 26(2): 42～47. (in Chinese)
[19] 陈旭. 沥青混凝土路面检测方法及影响因素研究[J]. 建材与装饰, 2018,(10): 311～312.Chen Xu. Research on asphalt concrete pavement testing methods and influencing factors[J]. Construction Materials & Decoration, 2018,(10): 311～312. (in Chinese)
[20] 尹德, 叶盛波, 张经纬等. 公路结构和介电特性对探地雷达反射回波的影响研究[J]. 电子测量技术, 2018, 41(5): 51～56.Yin De, Ye Shengbo, Zhang Jingwei et al. Study on the effect of highway structure and dielectric properties on GPR echo[J]. Electronic Measurement Technology, 2018, 41(5): 51～56. (in Chinese)
[21] 范文娟, 康迎宾. 基于地质雷达的隧道正演模拟研究综述[J]. 吉林水利, 2018,(1): 14～16.Fan Wenjuan, Kang Yingbin. A survey of tunnel forward modeling based on geological radar[J]. Jilin Water Resources, 2018,(1): 14～16. (in Chinese)
[2] 赵晓博. 隧道管波对于地震反射波法超前地质预报影响分析[J]. 工程勘察, 2018,(11): 74～78.Zhao Xiaobo. Analysis of influence of tunnel tube wave on geological forecast of seismic reflection wave method[J]. Geotechnical Investigation & Surveying, 2018,(11): 74～78. (in Chinese)
[3] 张劲松, 王星杰, 王晓岩. 隧道衬砌病害雷达检测定位精度分析[J]. 工程勘察, 2018, 46(4): 53～56.Zhang Jinsong, Wang Xingjie, Wang Xiaoyan. Detection and location of tunnel lining disease with radar[J]. Geotechnical Investigation & Surveying, 2018, 46(4): 53～56. (in Chinese)
[4] 秦镇, 吴海波, 张恩泽. 探地雷达在城市交通建设中的技术应用[J]. 西部探矿工程, 2018, 30(4): 95～98,103.Qin Zhen, Wu Haibo, Zhang Enze. Application of ground penetrating radar in urban traffic construction[J]. West-china Exploration Engineering, 2018, 30(4): 95～98,103. (in Chinese)
[5] 项雷. 公路隧道检测中探地雷达图像自动解释算法研究[D]. 南昌:南昌大学, 2013.Xiang Lei. Research on automatic interpretation algorithm of GPR image in highway tunnel detection[D]. Nanchang: Nanchang University, 2013. (in Chinese)
[6] 王春和, 胡通海, 崔海涛等. 探地雷达技术用于地下空洞塌陷灾害普查探测的创新与实践 [J]. 测绘通报, 2013,(S2): 13～16.Wang Chunhe, Hu Tonghai, Cui Haitao et al. The innovation and practice of ground penetrating radar technology used for disasters investigation especially for underground cavity or collapse detection[J]. Bulletin of Surveying and Mapping, 2013,(S2): 13～16. (in Chinese)
[7] 陈运飞, 刘士海, 李东海. 基于探地雷达技术的道路检测探究及应用[J]. 市政技术, 2018, 36(1): 20～22.Chen Yunfei, Liu Shihai, Li Donghai. Research and application of road detection based on ground penetrating radar technology[J]. Municipal Engineering Technology, 2018, 36(1): 20～22. (in Chinese)
[8] 周钰邦, 钟邱平, 马俊杰. 道路旁侧地下通道的物探响应特征[J]. 西南公路, 2018,(1): 48～52.Zhou Yubang, Zhong Qiuping, Ma Junjie. Geophysical response characteristics of roadside underground tunnels[J]. Southwest Highway, 2018,(1): 48～52. (in Chinese)
[9] 蒋维东, 黄欢, 贾茜淳等. 地质雷达在地下暗渠探测中的应用[J]. 人民珠江, 2018, 39(3): 42～48.Jiang Weidong, Huang Huan, Jia Xichun et al. Application of ground penetrating radar in underground drainage culvert detection[J]. Pearl River, 2018, 39(3): 42～48. (in Chinese)
[10] Lakshmi G, Panicker JR, Meera M. Named entity recognition in malayalam using fuzzy support vector machine[A]. Proceedings of 2016 International Conference on Information Science (ICIS) Kochi[C]. Japan, 2016, 201～206.
[11] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273～297.
[12] 刘方园, 王水花, 张煜东. 支持向量机模型与应用综述[J]. 计算机系统应用, 2018, 27(4): 1～9.Liu Fangyuan, Wang Shuihua, Zhang Yudong. Overview on models and applications of support vector machine[J]. Computer Systems & Applications, 2018, 27(4): 1～9. (in Chinese)
[13] 邹华胜. 路基病害识别算法与应用研究[J]. 地球物理学进展, 2009, 24(6): 2302～2307.Zou Huasheng. A study on roadbed disease recognition algorithm and application[J]. Progress in Geophysics, 2009, 24(6): 2302～2307. (in Chinese)
[14] Ryu J, Koo HI, Cho NI. Word segmentation method for handwritten documents based on structured learning[J]. IEEE Signal Processing Letters, 2015, 22(8): 1161～1165.
[15] Zhang ZM, Torr PHS. Object proposal generation using two-stage cascade SVMs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 102～115.
[16] Bo CJ, Lu HC and Wang D. Hyperspectral image classification via JCR and SVM models with decision fusion[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(2): 177～181.
[17] 张华美. 穿墙雷达基于支持向量机的成像算法研究[D]. 南京:南京邮电大学, 2015.Zhang Huamei. Study on imaging algorithm based on support vector machines for through-the-wall radars[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2015. (in Chinese)
[18] 周辉林, 姜玉玲, 徐立红等. 基于SVM的高速公路路基病害自动检测算法[J]. 中国公路学报, 2013, 26(2): 42～47.Zhou Huilin, Jiang Yuling, Xu Lihong et al. Automatic detection algorithm for expressway subgrade diseases based on SVM[J]. China Journal of Highway and Transport, 2013, 26(2): 42～47. (in Chinese)
[19] 陈旭. 沥青混凝土路面检测方法及影响因素研究[J]. 建材与装饰, 2018,(10): 311～312.Chen Xu. Research on asphalt concrete pavement testing methods and influencing factors[J]. Construction Materials & Decoration, 2018,(10): 311～312. (in Chinese)
[20] 尹德, 叶盛波, 张经纬等. 公路结构和介电特性对探地雷达反射回波的影响研究[J]. 电子测量技术, 2018, 41(5): 51～56.Yin De, Ye Shengbo, Zhang Jingwei et al. Study on the effect of highway structure and dielectric properties on GPR echo[J]. Electronic Measurement Technology, 2018, 41(5): 51～56. (in Chinese)
[21] 范文娟, 康迎宾. 基于地质雷达的隧道正演模拟研究综述[J]. 吉林水利, 2018,(1): 14～16.Fan Wenjuan, Kang Yingbin. A survey of tunnel forward modeling based on geological radar[J]. Jilin Water Resources, 2018,(1): 14～16. (in Chinese)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |