A Comprehensive Review of Conventional and Deep Learning Approaches for Ground-Penetrating Radar Detection of Raw Data
Source abstract
Abstract
Ground-penetrating radar (GPR) is a nondestructive testing technology that is widely applied in infrastructure maintenance, archaeological research, military operations, and other geological studies. A crucial step in GPR data processing is the detection and classification of underground structures and buried objects, including reinforcement bars, landmines, pipelines, bedrock, and underground cavities. With the development of machine learning algorithms, traditional methods such as SVM, K-NN, ANN, and HMM, as well as deep learning algorithms, have gradually been incorporated into A-scan, B-scan, and C-scan GPR image processing. This paper provides a summary of the typical machine learning and deep learning algorithms employed in the field of GPR and categorizes them based on the feature extraction method or classifier used. Additionally, this work discusses the sources and forms of data utilized in these studies. Finally, potential future development directions are presented.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geophysical Methods and Applications · Microwave Imaging and Scattering Analysis · Geophysical and Geoelectrical Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150006, China
Dalian Zoroy Technology Development Co., Ltd., Dalian 116085, China
Funding
National Natural Science Foundation of China
References (100+)
Show source-provided references
1. The Apollo lunar sounder radar system10.1109/PROC.1974.9517 ↗
2. Unterberger, R.R. (1992, January 8–13). Ground penetrating radar finds disturbed earth over burials. Proceedings of the Fourth International Conference on Ground Penetrating Radar, Rovaniemi, Finland.10.3997/2214-4609-pdb.303.44 ↗
3. Advanced image-processing technique for real-time interpretation of ground-penetrating radar images10.1002/(SICI)1098-1098(1998)9:1<51::AID-IMA7>3.0.CO;2-Q ↗
4. Artificial Neural Networks and Machine Learning techniques applied to Ground Penetrating Radar: A review10.1016/j.aci.2018.10.001 ↗
5. Advances of deep learning applications in ground-penetrating radar: A survey10.1016/j.conbuildmat.2020.120371 ↗
6. A Review of Target Detection Algorithm for GPR B-scan Processing
7. Pasolli, E., Melgani, F., Donelli, M., Attoui, R., and de Vos, M. (2008, January 7–11). Automatic Detection and Classification of Buried Objects in GPR Images Using Genetic Algorithms and Support Vector Machines. Proceedings of the 2018 IEEE International Geoscience and Remote Sensing Symposium, Boston, MA, USA.10.1109/IGARSS.2008.4779044 ↗
8. Material Classification of Underground Utilities From GPR Images Using DCT-Based SVM Approach10.1109/LGRS.2013.2261796 ↗
9. GPR identification of voids inside concrete based on the support vector machine algorithm10.1088/1742-2132/10/3/034002 ↗
10. Zhou, H., Feng, X., Zhang, Y., Nilot, E., Zhang, M., Dong, Z., and Qi, J. (2018, January 18–21). Combination of Support Vector Machine and H-Alpha Decomposition for Subsurface Target Classification of GPR. Proceedings of the 2018 17th International Conference on Ground Penetrating Radar (GPR), Rapperswil, Switzerland.10.1109/ICGPR.2018.8441522 ↗
11. Covariance-guided landmine detection and discrimination using ground-penetrating radar data10.1080/01431161.2017.1382746 ↗
12. A GPR-based Landmine Identification Method Using Energy and Dielectric Features
13. Comparison of histograms of oriented gradients (HOG) and n-Row average subtraction (nRAS) using GprMax10.1016/j.micpro.2018.08.011 ↗
14. Feature vector for underground object detection using B-scan images from GprMax
15. A Comparison of Feature Representations for Explosive Threat Detection in Ground Penetrating Radar Data10.1109/TGRS.2017.2732226 ↗
16. A Large-Scale Multi-Institutional Evaluation of Advanced Discrimination Algorithms for Buried Threat Detection in Ground Penetrating Radar10.1109/TGRS.2019.2909665 ↗
17. Ballan, M., and Gurgen, F. (2000, January 23–26). 2D ground penetrating radar data identification. Proceedings of the GPR 2000: Proceedings of the Eighth International Conference on Ground Penetrating Radar, Gold Coast, Australia.
18. Detection and Discrimination of Land Mines in Ground-Penetrating Radar Based on Edge Histogram Descriptors and a Possibilistic K-Nearest Neighbor Classifier10.1109/TFUZZ.2008.2005249 ↗
19. Elsaadouny, M., Barowski, J., and Rolfes, I. (2019, January 17–19). Humanitarian Microwave Imaging Enhancement and Classification of Shallowly Buried Objects. Proceedings of the 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) Technology, Vancouver, BC, Canada.10.1109/IEMCON.2019.8936165 ↗
20. Gray-statistics-based Twin Feature Extraction for Hyperbola Classification in Ground Penetrating Radar images10.1016/j.procs.2019.01.215 ↗
21. Gader, P.D., and Mystkowski, M. (1999, January 5–9). Applications of hidden Markov models to detecting land mines with ground-penetrating radar. Proceedings of the Detection and Remediation Technologies for Mines and Minelike Targets IV, Proceedings of AeroSense’99, Orlando, FL, USA.10.1117/12.356989 ↗
22. Landmine detection with ground penetrating radar using hidden Markov models10.1109/36.927446 ↗
23. Real-Time Landmine Detection with Ground-Penetrating Radar Using Discriminative and Adaptive Hidden Markov Models10.1155/ASP.2005.1867 ↗
24. Frigui, H., Missaoui, O., and Gader, P. (2007, January 9–13). Landmine detection using discrete hidden Markov models with Gabor features. Proceedings of the Detection and Remediation Technologies for Mines and Minelike Targets XII, Proceedings of Defense and Security Symposium, Orlando, FL, USA.10.1117/12.722241 ↗
25. Land-Mine Detection With Ground-Penetrating Radar Using Multistream Discrete Hidden Markov Models10.1109/TGRS.2010.2090886 ↗
26. Crevasse Detection in Ice Sheets Using Ground Penetrating Radar and Machine Learning10.1109/JSTARS.2014.2332872 ↗
27. Ensemble hidden Markov models with application to landmine detection10.1186/s13634-015-0260-8 ↗
28. Multiple-Instance Hidden Markov Model for GPR-Based Landmine Detection10.1109/TGRS.2014.2346954 ↗
29. Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition10.1016/S0926-9851(99)00055-5 ↗
30. Neural detection of pipe signatures in ground penetrating radar images10.1109/36.842008 ↗
31. Recognition technology for the detection of buried land mines10.1109/91.917112 ↗
32. Location of steel reinforcement in concrete using ground penetrating radar and neural networks10.1016/j.ndteint.2004.06.011 ↗
33. Birkenfeld, S. (2010, January 19–23). Automatic detection of reflexion hyperbolas in gpr data with neural networks. Proceedings of the 2010 World Automation Congress, Kobe, Japan.
34. Singh, N.P., and Nene, M.J. (2013, January 4–6). Buried object detection and analysis of GPR images: Using neural network and curve fitting. Proceedings of the 2013 Annual International Conference on Emerging Research Areas and 2013 International Conference on Microelectronics, Communications and Renewable Energy, Kanjirapally, India.10.1109/AICERA-ICMiCR.2013.6576024 ↗
35. GPR Signal Characterization for Automated Landmine and UXO Detection Based on Machine Learning Techniques10.3390/rs6109729 ↗
36. Classification of geological structure using ground penetrating radar and Laplace transform artificial neural networks10.1016/j.neucom.2014.06.025 ↗
37. Sparse Representation of GPR Traces With Application to Signal Classification10.1109/TGRS.2012.2228660 ↗
38. Terrasse, G., Nicolas, J., Trouvé, E., and Drouet, É. (September, January 29). Automatic localization of gas pipes from GPR imagery. Proceedings of the 2016 24th European Signal Processing Conference (EUSIPCO), Budapest, Hungary.10.1109/EUSIPCO.2016.7760678 ↗
39. Giovanneschi, F., Mishra, K.V., Gonzalez-Huici, M.A., Eldar, Y.C., and Ender, J.H.G. (2017, January 23–28). Online dictionary learning aided target recognition in cognitive GPR. Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA.10.1109/IGARSS.2017.8128079 ↗
40. Malof, J.M., Reichman, D., and Collins, L.M. (2017, January 10–12). Discriminative dictionary learning to learn effective features for detecting buried threats in ground penetrating radar data. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII, Proceedings of SPIE Defense + Security, Anaheim, CA, USA.10.1117/12.2263111 ↗
41. Deep dictionary learning application in GPR B-scan images10.1007/s11760-018-1313-x ↗
42. Dictionary Learning for Adaptive GPR Landmine Classification10.1109/TGRS.2019.2931134 ↗
43. Online dictionary learning method for extracting GPR diffractions10.1093/jge/gxz081 ↗
44. The Noise Attenuation and Stochastic Clutter Removal of Ground Penetrating Radar Based on the K-SVD Dictionary Learning10.1109/ACCESS.2021.3081349 ↗
45. GPR Clutter Reduction by Robust Orthonormal Subspace Learning10.1109/ACCESS.2020.2988333 ↗
46. Classification of Improvised Explosive Devices Using Multilevel Projective Dictionary Learning with Low-Rank Prior10.1109/TGRS.2022.3151335 ↗
47. Li, S., Tang, C., Li, Y., and Ye, F. (2022, January 1–3). Ground Penetrating Radar Microwave Denoising Based on Improved K-SVD Dictionary Learning Method. Proceedings of the 2022 International Conference on Microwave and Millimeter Wave Technology (ICMMT) Microwave and Millimeter Wave Technology (ICMMT), Harbin, China.10.1109/ICMMT55580.2022.10022934 ↗
48. A novel method for GPR imaging based on neural networks and dictionary learning10.1080/17455030.2021.1880667 ↗
49. Using dictionary learning for clutter reduction in GPR B-scan images10.1080/2150704X.2022.2161842 ↗
50. MUSIC-Based Super-Resolution CMP Velocity-Depth Analysis for Multilayer Cases10.1109/LGRS.2023.3235363 ↗
51. Automatic Analysis of GPR Images: A Pattern-Recognition Approach10.1109/TGRS.2009.2012701 ↗
52. Wu, J.B., Tian, M., and Ling, Y.T. (2009, January 24–26). Feature Extraction and Recognition Of landmine. Proceedings of the 2009 5th International Conference on Wireless Communications, Networking and Mobile Computing Wireless Communications, Networking and Mobile Computing, Beijing, China.10.1109/WICOM.2009.5302059 ↗
53. Pinar, A., Masarik, M., Havens, T.C., Burns, J., Thelen, B., and Becker, J. (2015, January 20–23). Approach to Explosive Hazard Detection Using Sensor Fusion and Multiple Kernel Learning with Downward-Looking GPR and EMI Sensor Data. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX, Baltimore, MD, USA.10.1117/12.2176856 ↗
54. Yuksel, S.E., Akar, G.B., and Ozturk, S. (2015, January 20–23). Fusion of forward-looking infrared camera and down-looking ground penetrating radar for buried target detection. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX, Baltimore, MD, USA.10.1117/12.2176735 ↗
55. Training DHMMs of mine and clutter to minimize landmine detection errors10.1109/TGRS.2003.811761 ↗
56. Using pattern recognition to automatically localize reflection hyperbolas in data from ground penetrating radar10.1016/j.cageo.2013.04.012 ↗
57. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
58. Besaw, L.E., and Stimac, P.J. (2015, January 20–24). Deep convolutional neural networks for classifying GPR B-scans. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX, Proceedings of SPIE Defense + Security, Baltimore, MD, USA.10.1117/12.2176250 ↗
59. Sakaguchi, R.T., Morton, K.D., Collins, L.M., and Torrione, P.A. (2015, January 20–24). Recognizing subsurface target responses in ground penetrating radar data using convolutional neural networks. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX, Proceedings of SPIE Defense + Security, Baltimore, MD, USA.10.1117/12.2177747 ↗
60. Besaw, L.E. (2016, January 3). Detecting buried explosive hazards with handheld GPR and deep learning. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXI, Proceedings of SPIE Defense + Security, Baltimore, MD, USA.10.1117/12.2223797 ↗
61. Sonoda, J., and Kimoto, T. (2018, January 6–9). Object Identification Form GPR Images by Deep Learning. Proceedings of the 2018 Asia-Pacific Microwave Conference (APMC), Kyoto, Japan.10.23919/APMC.2018.8617556 ↗
62. GPR B scan image analysis with deep learning methods10.1016/j.measurement.2020.107770 ↗
63. Bralich, J., Reichman, D., Collins, L.M., and Malof, J.M. (2017, January 10–12). Improving convolutional neural networks for buried target detection in ground penetrating radar using transfer learning via pretraining. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII, Proceedings of SPIE Defense + Security, Anaheim, CA, USA.10.1117/12.2263112 ↗
64. Reichman, D., Collins, L.M., and Malof, J.M. (2017, January 28–30). Some good practices for applying convolutional neural networks to buried threat detection in Ground Penetrating Radar. Proceedings of the 2017 9th International Workshop on Advanced Ground Penetrating Radar (IWAGPR), Edinburgh, UK.10.1109/IWAGPR.2017.7996100 ↗
65. Lameri, S., Lombardi, F., Bestagini, P., Lualdi, M., and Tubaro, S. (September, January 28). Landmine detection from GPR data using convolutional neural networks. Proceedings of the 2017 25th European Signal Processing Conference (EUSIPCO), Kos, Greece.10.23919/EUSIPCO.2017.8081259 ↗
66. An algorithm for automatic localization and detection of rebars from GPR data of concrete bridge decks10.1016/j.autcon.2018.02.017 ↗
67. Aydin, E., and Yuksel Erdem, S.E. (2019, January 15–17). Transfer and Multitask Learning using Convolutional Neural Networks for Buried Wire Detection from Ground Penetrating Radar Data. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV, Baltimore, MD, USA.10.1117/12.2518875 ↗
68. Automatic detection of moisture damages in asphalt pavements from GPR data with deep CNN and IRS method10.1016/j.autcon.2020.103119 ↗
69. Pham, M., and Lefèvre, S. (2018, January 22–27). Buried Object Detection from B-Scan Ground Penetrating Radar Data Using Faster-RCNN. Proceedings of the 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.10.1109/IGARSS.2018.8517683 ↗
70. Autonomous pavement distress detection using ground penetrating radar and region-based deep learning10.1016/j.measurement.2020.108077 ↗
71. Railway Subgrade Defect Automatic Recognition Method Based on Improved Faster R-CNN
72. Automatic hyperbola detection and fitting in GPR B-scan image10.1016/j.autcon.2019.102839 ↗
73. A Study of Automatic Recognition and Localization of Pipeline for Ground Penetrating Radar Based on Deep Learning10.1109/LGRS.2022.3198439 ↗
74. Automatic recognition and tracking of highway layer-interface using Faster R-CNN10.1016/j.jappgeo.2021.104477 ↗
75. Improved Mask R-CNN with distance guided intersection over union for GPR signature detection and segmentation10.1016/j.autcon.2020.103414 ↗
76. Deep Learning-Based Subsurface Target Detection From GPR Scans10.1109/JSEN.2021.3050262 ↗
77. Automatic pixel-level detection of vertical cracks in asphalt pavement based on GPR investigation and improved mask R-CNN10.1016/j.autcon.2022.104689 ↗
78. Besaw, L.E., and Stimac, P.J. (2014, January 5–7). Deep learning algorithms for detecting explosive hazards in ground penetrating radar data. Proceedings of the Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XIX, Proceedings of SPIE Defense + Security, Baltimore, MD, USA.10.1117/12.2052592 ↗
79. Nguyen, T.T., Tung, P.T., Tan, N.N., Linh, N.N., and Luc, T.T. (2022). A Study of Factors Affecting GPR Signal Amplitudes in Reinforced Structures Using Deep Belief Networks. Infrastructures, 7.10.3390/infrastructures7090123 ↗
80. Picetti, F., Testa, G., Lombardi, F., Bestagini, P., Lualdi, M., and Tubaro, S. (2018, January 4–6). Convolutional Autoencoder for Landmine Detection on GPR Scans. Proceedings of the 2018 41st International Conference on Telecommunications and Signal Processing (TSP), Athens, Greece.10.1109/TSP.2018.8441206 ↗
81. Detection and localization of rebar in concrete by deep learning using ground penetrating radar10.1016/j.autcon.2020.103279 ↗
82. Wang, Z., Lan, T., Qu, X., Gao, S., Yu, Z., and Yang, X. (2021, January 15–19). Improved SSD Framework for Automatic Subsurface Object Indentification for GPR Data Processing. Proceedings of the 2021 CIE International Conference on Radar (Radar), Haikou, China.10.1109/Radar53847.2021.10028347 ↗
83. Lei, W., Luo, J., Hou, F., Xu, L., Wang, R., and Jiang, X. (2020). Underground Cylindrical Objects Detection and Diameter Identification in GPR B-Scans via the CNN-LSTM Framework. Electronics, 9.10.3390/electronics9111804 ↗
84. Residual CNN plus Bi-LSTM model to analyze GPR B scan images10.1016/j.autcon.2020.103525 ↗
85. Juan, H., Longxiang, W., and Hongxia, Y. (2021, January 28–31). A new Wavelet Prediction method for GPR clutter elimination Based on LSTM network. Proceedings of the 2021 International Applied Computational Electromagnetics Society (ACES-China) Symposium, Chengdu, China.10.23919/ACES-China52398.2021.9581488 ↗
86. GPRI2Net: A Deep-Neural-Network-Based Ground Penetrating Radar Data Inversion and Object Identification Framework for Consecutive and Long Survey Lines
87. Yue, Y.P., Liu, H., Meng, X., Li, Y.G., and Du, Y.L. (2021). Generation of High-Precision Ground Penetrating Radar Images Using Improved Least Square Generative Adversarial Networks. Remote Sens., 13.10.3390/rs13224590 ↗
88. Declutter-GAN: GPR B-Scan Data Clutter Removal Using Conditional Generative Adversarial Nets10.1109/LGRS.2022.3159788 ↗
89. Reconstructing unseen spaces in collapsed structures for search and rescue via deep learning based radargram inversion10.1016/j.autcon.2022.104380 ↗
90. Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models10.1109/ACCESS.2023.3243132 ↗
91. Kang, M.-S., Kim, N., Im, S.B., Lee, J.-J., and An, Y.-K. (2019). 3D GPR Image-based UcNet for Enhancing Underground Cavity Detectability. Remote Sens., 11.10.3390/rs11212545 ↗
92. Triplanar Imaging of 3-D GPR Data for Deep-Learning-Based Underground Object Detection10.1109/JSTARS.2019.2953505 ↗
93. Three-dimensional convolutional neural network–based underground object classification using three-dimensional ground penetrating radar data10.1177/1475921720902700 ↗
94. Application of Convolutional and Recurrent Neural Networks for Buried Threat Detection Using Ground Penetrating Radar Data10.1109/TGRS.2020.2978763 ↗
95. Dai, Q., Lee, Y.H., Sun, H.H., Yucel, A.C., Ow, G., and Yusof, M.L.M. (2021, January 4–10). A Deep Learning Scheme for Rapidly Reconstructing 3D Permittivity Maps from GPR C-scans. Proceedings of the 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI), Singapore.10.1109/APS/URSI47566.2021.9703958 ↗
96. Li, N.S., Wu, R.B., Li, H.F., Wang, H.C., Gui, Z.C., and Song, D.Z. (2022). MV-GPRNet: Multi-View Subsurface Defect Detection Network for Airport Runway Inspection Based on GPR. Remote Sens., 14.10.3390/rs14184472 ↗
97. Reconstruction of Subsurface Objects by LSM and FWI From Limited-Aperture Electromagnetic Data10.1109/TGRS.2021.3109086 ↗
98. Automatic recognition of pavement cracks from combined GPR B-scan and C-scan images using multiscale feature fusion deep neural networks10.1016/j.autcon.2022.104698 ↗
99. Xiang, Z., Rashidi, A., and Ou, G. (2019, January 17–19). An Improved Convolutional Neural Network System for Automatically Detecting Rebar in GPR Data. Proceedings of the 2019 ASCE International Conference on Computing in Civil Engineering, Atlanta, GA, USA.10.1061/9780784482438.054 ↗
100. He, Y., Li, B., Guo, Y., Wang, T., and Zhu, Y. (2016, January 29–31). An interpretation model of GPR point data in tunnel geological prediction. Proceedings of the Eighth International Conference on Graphic and Image Processing, Tokyo, Japan.10.1117/12.2266226 ↗