Automatic Classification of Ground-Penetrating-Radar Signals for Railway-Ballast Assessment

被引:74
作者
Shao, Wenbin [1 ]
Bouzerdoum, Abdesselam
Son Lam Phung
Su, Lijun [1 ,2 ]
Indraratna, Buddhima
Rujikiatkamjorn, Cholachat
机构
[1] Univ Wollongong, Fac Engn, Cooperat Res Ctr Rail Innovat, Wollongong, NSW 2522, Australia
[2] Xian Univ Architecture & Technol, Sch Civil Engn, Xian 710055, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2011年 / 49卷 / 10期
基金
澳大利亚研究理事会;
关键词
Ground-penetrating radar (GPR) processing; railway-ballast assessment; support vector machine (SVM);
D O I
10.1109/TGRS.2011.2128328
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
The ground-penetrating radar (GPR) has been widely used in many applications. However, the processing and interpretation of the acquired signals remain challenging tasks since an experienced user is required to manage the entire operation. In this paper, we present an automatic classification system to assess railway-ballast conditions. It is based on the extraction of magnitude spectra at salient frequencies and their classification using support vector machines. The system is evaluated on real-world railway GPR data. The experimental results show that the proposed method efficiently represents the GPR signal using a small number of coefficients and achieves a high classification rate when distinguishing GPR signals reflected by ballasts of different conditions.
引用
收藏
页码:3961 / 3972
页数:12
相关论文
共 33 条
[1]  
Abe S., 2005, ADV PTRN RECOGNIT
[2]   Time-frequency approach for ground penetrating radar data analysis to assess railroad ballast condition [J].
Al-Qadi, Imad L. ;
Xie, Wei ;
Roberts, Roger .
RESEARCH IN NONDESTRUCTIVE EVALUATION, 2008, 19 (04) :219-237
[3]  
Allred BJ, 2008, BOOKS SOIL PLANT ENV, P1
[4]  
Annan A.P., 2002, SUBSURFACE SENSING T, V3, P253, DOI [DOI 10.1023/A:1020657129590, 10.1023/A:1020657129590]
[5]  
[Anonymous], INT J INF SYST SCI
[6]  
[Anonymous], 2001, Pattern Classification
[7]  
[Anonymous], 2006, Pattern recognition and machine learning
[8]  
[Anonymous], 2010, P 13 INT C GROUND PE
[9]  
Chang C.-C., 2007, LIBSVM: a Library for Support Vector Machines
[10]  
Cristianini N., 2001, An Introduction to Support Vector Machines