Material Classification of Underground Utilities From GPR Images Using DCT-Based SVM Approach

被引:52
作者
El-Mahallawy, Mohamed S. [1 ]
Hashim, Mazlan [2 ]
机构
[1] Arab Acad Sci Technol & Maritime Transport, Cairo, Egypt
[2] Univ Teknol Malaysia, Inst Geospatial Sci & Technol, Johor Baharu 81310, Malaysia
关键词
Discrete cosine transform (DCT); feature extraction; ground penetrating radar (GPR); support vector machine (SVM); underground utilities; RADAR;
D O I
10.1109/LGRS.2013.2261796
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
In this letter, we introduce the utilization of discrete cosine transform (DCT) coefficients as features supplied to the support vector machine (SVM) classifier to identify underground utility material from ground penetrating radar (GPR) imagery. Different types of features, reflected signal amplitudes, and statistical features, combined with the SVM classifier for material identification of underground utilities, are also studied and compared to the DCT-based approach. The system performance is conducted by simulation studies using generated GPR images created by a GPR finite-difference time-domain-based simulator used to develop various acquisition situations by changing the utility material type, position, and size parameters. The efficiency of the proposed technique in material identification is assessed using noisy generated GPR images degraded with speckle noise. Two-dimensional median and adaptive Wiener filters are also examined as a preprocessing step to the studied techniques. Simulation results show that the proposed technique combined with adaptive Wiener filter reveals a good performance regarding the recognition accuracy compared to the other studied techniques in noisy environment.
引用
收藏
页码:1542 / 1546
页数:5
相关论文
共 15 条
[1]   Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition [J].
Al-Nuaimy, W ;
Huang, Y ;
Nakhkash, M ;
Fang, MTC ;
Nguyen, VT ;
Eriksen, A .
JOURNAL OF APPLIED GEOPHYSICS, 2000, 43 (2-4) :157-165
[2]  
[Anonymous], 2003, PRACTICAL GUIDE SUPP
[3]  
[Anonymous], 2000, ACM SIGKDD EXPLOR NE, DOI DOI 10.1145/380995.380999
[4]   The detection of buried pipes from time-of-flight radar data [J].
Borgioli, Giovanni ;
Capineri, Lorenzo ;
Falorni, PierLuigi ;
Matucci, Serena ;
Windsor, Colin G. .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (08) :2254-2266
[5]  
Falorni P, 2004, PROCEEDINGS OF THE TENTH INTERNATIONAL CONFERENCE ON GROUND PENETRATING RADAR, VOLS 1 AND 2, P403
[6]   Modelling ground penetrating radar by GprMax [J].
Giannopoulos, A .
CONSTRUCTION AND BUILDING MATERIALS, 2005, 19 (10) :755-762
[7]   A comparison of methods for multiclass support vector machines [J].
Hsu, CW ;
Lin, CJ .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (02) :415-425
[8]   Adaptive filtering of random noise in near-surface seismic and ground-penetrating radar data [J].
Jeng, Yih ;
Li, Yi-Wei ;
Chen, Chih-Sung ;
Chien, Hsin-Yi .
JOURNAL OF APPLIED GEOPHYSICS, 2009, 68 (01) :36-46
[9]   Detection of landmines and underground utilities from acoustic and GPR images with a cepstral approach [J].
Khan, Umar S. ;
Al-Nuaimy, Waleed ;
Abd El-Samie, Fathi E. .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2010, 21 (07) :731-740
[10]  
Lim J. S., 1990, Two-Dimensional Signal and Image Processing