volume | PIER Journals

Abstract

As a popular nondestructive technique, ground penetrating radar (GPR) is extensively utilized for detecting underground pipelines. In this paper, an efficient and automatic scheme is presented for the detection and classification of underground pipelines by combining electromagnetic modeling and machine learning techniques. By virtue of open-source gprMax software, the B-Scan signatures of underground pipelines are simulated and analyzed in detail, with four types of underground pipelines taken into account, i.e., iron pipelines, concrete pipelines, copper pipelines, and PVC pipelines. On the basis of electromagnetic modeling, B-scan profiles of underground pipelines are preprocessed by using the average method and time gain compensation method to obtain a dataset for training neural network of YOLOv8 model. The simulations indicate that our scheme combining simulated B-Scan profiles and YOLOv8 model is able to detect and classify underground pipelines with high accuracy, and the category and material of underground pipelines can be determined with a high confidence level. Specifically, the detection time of a single B-scan image for underground pipelines is about 0.02s, and the average detection accuracy can reach 0.995, which is potentially valuable for the automatic detection and classification of underground pipelines in GPR applications.

1. Frigui, Hichem and Paul Gader, "Detection and discrimination of land mines in ground-penetrating radar based on edge histogram descriptors and a possibilistic K-nearest neighbor classifier," IEEE Transactions on Fuzzy Systems, Vol. 17, No. 1, 185-199, 2008. Google Scholar

2. Muggleton, J. M., M. J. Brennan, and Y. Gao, "Determining the location of buried plastic water pipes from measurements of ground surface vibration," Journal of Applied Geophysics, Vol. 75, No. 1, 54-61, 2011. Google Scholar

3. Sagnard, Florence and Jean-Philippe Tarel, "Template-matching based detection of hyperbolas in ground-penetrating radargrams for buried utilities," Journal of Geophysics and Engineering, Vol. 13, No. 4, 491-504, 2016. Google Scholar

4. Tong, Zheng, Jie Gao, and Dongdong Yuan, "Advances of deep learning applications in ground-penetrating radar: A survey," Construction and Building Materials, Vol. 258, 120371, 2020. Google Scholar

5. Bai, Xu, Yu Yang, Shouming Wei, Guanyi Chen, Hongrui Li, Yuhao Li, Haoxiang Tian, Tianxiang Zhang, and Haitao Cui, "A comprehensive review of conventional and deep learning approaches for ground-penetrating radar detection of raw data," Applied Sciences, Vol. 13, No. 13, 7992, 2023. Google Scholar

6. Al-Nuaimy, W., Y. Huang, M. Nakhkash, M. T. C. Fang, V. T. Nguyen, and A. Eriksen, "Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition," Journal of Applied Geophysics, Vol. 43, No. 2-4, 157-165, 2000. Google Scholar

7. Kaur, Parneet, Kristin J. Dana, Francisco A. Romero, and Nenad Gucunski, "Automated GPR rebar analysis for robotic bridge deck evaluation," IEEE Transactions on Cybernetics, Vol. 46, No. 10, 2265-2276, 2016. Google Scholar

8. Dou, Qingxu, Lijun Wei, Derek R. Magee, and Anthony G. Cohn, "Real-time hyperbola recognition and fitting in GPR data," IEEE Transactions on Geoscience and Remote Sensing, Vol. 55, No. 1, 51-62, 2017. Google Scholar

9. Pasolli, Edoardo, Farid Melgani, and Massimo Donelli, "Automatic analysis of GPR images: A pattern-recognition approach," IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 7, 2206-2217, 2009. Google Scholar

10. Wong, Phoebe Tin-Wai, Wallace Wai-Lok Lai, and Chi-Sun Poon, "Classification of concrete corrosion states by GPR with machine learning," Construction and Building Materials, Vol. 402, 132855, 2023. Google Scholar

11. Xu, Hong, Jie Yan, Guangliang Feng, Zhuo Jia, and Peiqi Jing, "Rock layer classification and identification in ground-penetrating radar via machine learning," Remote Sensing, Vol. 16, No. 8, 1310, 2024. Google Scholar

12. Xue, Wei, Kehui Chen, Ting Li, Li Liu, and Jian Zhang, "Efficient underground target detection of urban roads in ground-penetrating radar images based on neural networks," Remote Sensing, Vol. 15, No. 5, 1346, 2023. Google Scholar

13. Kandasamy, Lalitha and Shreya Reddy, "Deep learning algorithm for automatic breast tumour detection and classification from electromagnetic scattering data," Progress In Electromagnetics Research C, Vol. 128, 39-48, 2022. Google Scholar

14. Versaci, Mario, Giovanni Angiulli, Paolo Crucitti, Domenico De Carlo, Filippo Lagana, Diego Pellicanò, and Annunziata Palumbo, "A fuzzy similarity-based approach to classify numerically simulated and experimentally detected carbon fiber-reinforced polymer plate defects," Sensors, Vol. 22, No. 11, 4232, 2022.
doi:10.3390/s22114232 Google Scholar

15. Iftimie, Nicoleta, Adriana Savin, Rozina Steigmann, and Gabriel Silviu Dobrescu, "Underground pipeline identification into a non-destructive case study based on ground-penetrating radar imaging," Remote Sensing, Vol. 13, No. 17, 3494, 2021. Google Scholar

16. Ganiyu, S. A., M. A. Oladunjoye, O. I. Onakoya, J. O. Olutoki, and B. S. Badmus, "Combined electrical resistivity imaging and ground penetrating radar study for detection of buried utilities in Federal University of Agriculture, Abeokuta, Nigeria," Environmental Earth Sciences, Vol. 79, 1-20, 2020. Google Scholar

17. Iftimie, N., A. Savin, N. A. Danila, and G. S. Dobrescu, "Radar pulses to image the subsurface using Ground Penetrating Radar (GPR)," IOP Conference Series: Materials Science and Engineering, Vol. 564, No. 1, 012130, 2019.

18. Prego, F. J., M. Solla, I. Puente, and P. Arias, "Efficient GPR data acquisition to detect underground pipes," NDT & E International, Vol. 91, 22-31, 2017. Google Scholar

19. Benedetto, Andrea, Fabio Tosti, Luca Bianchini Ciampoli, and Fabrizio D'amico, "An overview of ground-penetrating radar signal processing techniques for road inspections," Signal Processing, Vol. 132, 201-209, 2017. Google Scholar

20. Saarenketo, Timo and Tom Scullion, "Road evaluation with ground penetrating radar," Journal of Applied Geophysics, Vol. 43, No. 2-4, 119-138, 2000. Google Scholar

21. Rasol, Mezgeen, Jorge C. Pais, Vega Pérez-Gracia, Mercedes Solla, Francisco M. Fernandes, Simona Fontul, David Ayala-Cabrera, Franziska Schmidt, and Hossein Assadollahi, "GPR monitoring for road transport infrastructure: A systematic review and machine learning insights," Construction and Building Materials, Vol. 324, 126686, 2022. Google Scholar

22. Torrione, Peter A., Kenneth D. Morton, Rayn Sakaguchi, and Leslie M. Collins, "Histograms of oriented gradients for landmine detection in ground-penetrating radar data," IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, No. 3, 1539-1550, 2013. Google Scholar

23. Liu, Hai, Chunxu Lin, Jie Cui, Lisheng Fan, Xiongyao Xie, and Billie F. Spencer, "Detection and localization of rebar in concrete by deep learning using ground penetrating radar," Automation in Construction, Vol. 118, 103279, Oct. 2020. Google Scholar

24. Ma, Xiao, Yangjia Li, and Jiaxing Song, "A stable auxiliary differential equation perfectly matched layer condition combined with low-dispersive symplectic methods for solving second-order elastic wave equations," Geophysics, Vol. 84, No. 4, T193-T206, 2019. Google Scholar

25. El Mahgoub, Khaled, Atef Z. Elsherbeni, and Fan Yang, "Dispersive periodic boundary conditions for finite-difference time-domain method," IEEE Transactions on Antennas and Propagation, Vol. 60, No. 4, 2118-2122, 2012. Google Scholar

26. Lu, Tiao, Pingwen Zhang, and Wei Cai, "Discontinuous Galerkin methods for dispersive and lossy Maxwell's equations and PML boundary conditions," Journal of Computational Physics, Vol. 200, No. 2, 549-580, 2004. Google Scholar

27. Warren, Craig, Antonios Giannopoulos, and Iraklis Giannakis, "gprMax: Open source software to simulate electromagnetic wave propagation for ground penetrating radar," Computer Physics Communications, Vol. 209, 163-170, 2016. Google Scholar

28. Howlader, Md. Omar Faruq and Tariq Pervez Sattar, "FDTD based numerical framework for ground penetrating radar simulation," Progress In Electromagnetics Research M, Vol. 44, 127-138, 2015. Google Scholar

29. Peplinski, Neil R., Fawwaz T. Ulaby, and Myron Craig Dobson, "Corrections to ``Dielectric properties of soils in the 0.3-1.3-GHz range''," IEEE Transactions on Geoscience and Remote Sensing, Vol. 33, No. 6, 1340, 1995. Google Scholar

30. Giannopoulos, Antonis, "Modelling ground penetrating radar by gprMax," Construction and Building Materials, Vol. 19, No. 10, 755-762, 2005. Google Scholar

31. Ayala-Cabrera, David, Manuel Herrera, Joaquín Izquierdo, and Rafael Pérez-García, "Location of buried plastic pipes using multi-agent support based on GPR images," Journal of Applied Geophysics, Vol. 75, No. 4, 679-686, 2011. Google Scholar

32. Ahrens, James, Berk Geveci, and Charles Law, ParaView: An End-User Tool for Large-Data Visualization, 717-731, Butterworth-Heinemann, Burlington, 2005.

33. Soldovieri, Francesco, Ilaria Catapano, Pier Matteo Barone, Sebastian E. Lauro, Elisabetta Mattei, Elena Pettinelli, Guido Valerio, Davide Comite, and Alessandro Galli, "GPR estimation of the geometrical features of buried metallic targets in testing conditions," Progress In Electromagnetics Research B, Vol. 49, 339-362, 2013. Google Scholar

34. Gamba, Paolo and Simone Lossani, "Neural detection of pipe signatures in ground penetrating radar images," IEEE Transactions on Geoscience and Remote Sensing, Vol. 38, No. 2, 790-797, 2000. Google Scholar

35. Talaat, Fatma M. and Hanaa Zain Eldin, "An improved fire detection approach based on YOLO-v8 for smart cities," Neural Computing and Applications, Vol. 35, No. 28, 20939-20954, 2023. Google Scholar

36. Yu, Hang, Jianguo Wang, Yaxiong Han, Bin Fan, and Chao Zhang, "Research on an intelligent identification method for wind turbine blade damage based on CBAM-BiFPN-YOLOV8," Processes, Vol. 12, No. 1, 205, 2024. Google Scholar

37. Chicco, Davide, Niklas Tötsch, and Giuseppe Jurman, "The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation," BioData Mining, Vol. 14, No. 1, 1-22, 2021. Google Scholar

38. Gader, Paul D., Bruce N. Nelson, Hichem Frigui, Gary Vaillette, and James M. Keller, "Fuzzy logic detection of landmines with ground penetrating radar," Signal Processing, Vol. 80, No. 6, 1069-1084, 2000. Google Scholar

39. Dinh, Kien, Nenad Gucunski, and Trung H. Duong, "An algorithm for automatic localization and detection of rebars from GPR data of concrete bridge decks," Automation in Construction, Vol. 89, 292-298, 2018. Google Scholar

40. Wang, Yanhui, Guangyan Cui, and Jun Xu, "Semi-automatic detection of buried rebar in GPR data using a genetic algorithm," Automation in Construction, Vol. 114, 103186, 2020. Google Scholar

41. Maas, Christian and Jörg Schmalzl, "Using pattern recognition to automatically localize reflection hyperbolas in data from ground penetrating radar," Computers & Geosciences, Vol. 58, 116-125, 2013. Google Scholar

42. Ozkaya, Umut, Farid Melgani, Mesay Belete Bejiga, Levent Seyfi, and Massimo Donelli, "GPR B scan image analysis with deep learning methods," Measurement, Vol. 165, 107770, 2020. Google Scholar

Dr. Qiang Guo

Dr. Peng-Ju Yang

Dr. Rui Wu

Dr. Yuqiang Zhang