Abstract
This study combines ground penetrating radar (GPR) and convolutional neural networks for the intelligent detection of underground road targets. The target location was realized using a gradient-class activation map (Grad-CAM). First, GPR technology was used to detect roads and obtain radar images. This study constructs a radar image dataset containing 3000 underground road radar targets, such as underground pipelines and holes. Based on the dataset, a ResNet50 network was used to classify and train different underground targets. During training, the accuracy of the training set gradually increases and finally fluctuates approximately 85%. The loss function gradually decreases and falls between 0.2 and 0.3. Finally, targets were located using Grad-CAM. The positioning results of single and multiple targets are consistent with the actual position, indicating that the method can effectively realize the intelligent detection of underground targets in GPR.
Similar content being viewed by others
References
Baker, G. S., Jordan, T. E., Pardy, J., et al., 2007, An introduction to ground penetrating radar (gpr): SPECIAL PAPERS-GEOLOGICAL SOCIETY OF AMERICA, 432: 1.
Benson, A. K., 1995, Applications of ground penetrating radar in assessing some geological hazards: examples of groundwater contamination, faults, cavities: Journal of Applied Geophysics, 33(1–3):177–193.
Besaw, L. E., Stimac, P. J., 2015, Deep convolutional neural networks for classifying GPR B-scans: Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XX, 9454.
Chen, K., 2021, Research on Railway Tool Image Classification and Detection Method Based on Deep Learning: Hunan University.
Davis, J. L., Annan, A. P., 1989, GROUND-PENETRATING RADAR FOR HIGH-RESOLUTION MAPPING OF SOIL AND ROCK STRATIGRAPHY1: Geophysical Prospecting, 37(5).
Fan, C., Mn, A., Js, E., et al., 2021, Automatic recognition and tracking of highway layer-interface using Faster R-CNN - ScienceDirect.
Feng, D. S., Yang, Z. L., 2020, Automatic recognition of ground penetrating radar image of tunnel lining structure based on deep learning: Progress in Geophysics, 35(04): 1552–1556.
Girshick, R., Donahue, J., Darrell, T., et al., 2013, Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation: IEEE Computer Society.
Hao, T., Zhao, J., 2019, A Brief Review of the Hyperbola Signature Recognition Techniques for Ground Penetrating Radar: ACTA ELECT RONICA SINICA, 47(6): 1366–1372.
He, K., Zhang, X., Ren, S., et al., 2016, Deep residual learning for image recognition: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: 770–778.
Hinton, G. E., Salakhutdinov, R. R., 2006, Reducing the dimensionality of data with neural networks: science, 313(5786): 504–507.
Kang, M. S., Kim, N., Im, S. B., et al., 2019, 3D GPR Image-based UcNet for Enhancing Underground Cavity Detectability: Remote Sensing, 11(21):2545-.
Krizhevsky, A., Sutskever, I., Hinton, G.E., 2012, ImageNet Classification with Deep Convolutional Neural Networks: Advances in neural information processing systems, 25(2).
Lameri, S., Lombardi, F., Bestagini, P., Lualdi, M., Tubaro, S., 2017, Landmine detection from GPR data using convolutional neural networks: 2017 25th European Signal Processing Conference (EUSIPCO).
Liao, B. B., 2019, Research on the Application of Deep Learning in Target Recognition of Ground Penetrating Radar: School of Resources and Environment.
Liang, X. M., Ni, F., Chen, W. J., Zhang, J. S., 2022, Interpretability of Modulation Recognition Network Based on Time-Frequency Grad-CAM: Journal of Southwest Jiaotong University: 1–9.
Liu, Q., Zhang, N., Yang, W., et al., 2017, A review of image recognition with deep convolutional neural network: International Conference on Intelligent Computing, 69–80.
Neal, A., 2004, Ground-penetrating radar and its use in sedimentology: principles, problems and progress: Earth-science reviews, 66(3–4): 261–330.
Ozkaya, U., Ztürk, A., Melgani, F., et al., 2021, Residual CNN plus Bi-LSTM model to analyze GPR B scan images: Automation in Construction, 123:103525.
Pablo, B., Bonomo, N., Patricia, M., 2019, Automatic detection of pipe-flange reflections in GPR data sections using super-vised learning: Journal of Applied Geophysics, 170: 103856.
Peng, S., Yang, F., 2004, Fine geological radar processing and interpretation: Applied Geophysics, 1(2):89–94.
Selvaraju, R. R., Cogswell, M., Das, A., et al., 2017, Grad-cam: visual explanations from deep networks via gradient-based localization: Proceedings of the IEEE International Conferenceon Computer Vision: 618–626.
Selvaraju, R. R., Das, A., Vedantam, R., et al., 2016, Grad-CAM: why did you say that?: Ar**v Preprint. Ar**v:1611.07450.
Smith, D., 1995, Ground-penetrating radar: antenna frequencies and maximum probable depths of penetration in Quaternary sediments: Journal of Applied Geophysics, 33(1–3):93–100.
Tang, Y. H., Wei, D. H., Suo, L., Lv, F., Zhao, S. W., Ma, W. D., 2021, Application of Seismic Imaging Method and Ground Penetrating Radar Method in Karst Detection at the Bottom of Railroad Tunnels: CHINESE JOURNAL OF ENGINEERING GEOPHYSICS, 18(05): 665–670.
Vargas, R., Mosavi, A., Ruiz, R., 2017, Deep learning: A review: Advances in Intelligent Systems and Computing, 5.
Wen, H., Zhang, D., Zheng, X.Z., et al., 2017, Propagation characteristics of electromagnetic wave based on FDTD in coal: JOURNAL OF CHINA COAL SOCIETY, 42(11): 2959–2967.
**e, Y. L., Deng, H. F., 2022, A Radio Frequency Fingerprinting Identification Method Based on Improved ResNet: Telecommunication Engineering, 62(04): 416–423.
Xu, X., Lei, Y., Yang, F., 2018, Railway Subgrade Defect Automatic Recognition Method Based on Improved Faster R-CNN: Scientific programming, 2018(PT.2): 4832972.1–4832972.12.
Zhao, B., Li, P., Dai, M. R., et al., 2019, Research on Optimization Method of Railway Image Scene Classification Based on Deep: Computer Systems & Applications, 28(06):228–234.
Zhao, D., Ye, S. B., Zhou, B., 2020, Ground penetrating radar anomaly detection based on convolution Grad-CAM: ELECTRONIC MEASUREMENT TECHNOLOGY, 43(10): 113–118.
Zhang, X., 2022, Research on Tunnel Fire Warning Based on Intelligent Image Processing Technology: Shenyang University of Technology.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported in part by the National Natural Science Fund of China under Grant 52074306, in part by the National Key Research and Development Program of China under Grant 2019YFC1805504 and in part by the Fundamental Research Funds for the Central Universities under Grant 2023JCCXHH02.
Dou Yi-Tao is currently a master’s degree candidate. She graduated from the Nan**g University of Posts and Telecommunications with a B.S. degree in Human Geography and Urban-Rural Planning in 2021 (graduation). Since 2021, she has been pursuing her M.S. degree in Cartography and Geographic Information System at the China University of Mining & Technology, Bei**g. Her main interests are geophysical prospecting and machine learning.
Rights and permissions
About this article
Cite this article
Dou, YT., Dong, GQ. & Li, X. Automatic identification of GPR targets on roads based on CNN and Grad-CAM. Appl. Geophys. (2024). https://doi.org/10.1007/s11770-024-1105-8
Received:
Revised:
Published:
DOI: https://doi.org/10.1007/s11770-024-1105-8