Subsurface Object 3D Modeling Based on Ground Penetration Radar Using Deep Neural Network
Publication: Journal of Computing in Civil Engineering
Volume 37, Issue 6
Abstract
In numerous infrastructure health monitoring and inspection applications, swift and precise three-dimensional reconstruction of subsurface objects from ground penetrating radar (GPR) data is of critical importance, particularly given the recent advancements in perception modeling and the emergence of deep learning. Nonetheless, current research on the reconstruction of subsurface infrastructure scenes and objects faces limitations. Owing to the restrictions of conventional GPR data processing, these methodologies are prone to GPR data with noisy backgrounds and struggle to recreate noncylindrical objects. This paper investigates the back-projection (BP) approach for GPR-based three-dimensional (3D) subsurface target reconstruction and presents a learning model that formulates the reconstruction as an implicit BP from 2D to 3D representations, circumventing any preprocessing requirements in contrast to traditional techniques. The proposed learned model ultimately generates an explicit volumetric representation of the subsurface objects. Experimental results show at least a 33% enhancement in the performance of the proposed model compared to meticulously designed baselines.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are available in a repository online in accordance with funder data retention policies. The data and code can be found at https://github.com/Jing-lun/GPR_3D_Model_Reconstruction.
Acknowledgments
Financial support for this study was provided by NSF Grant IIP-1915721, and by the US Department of Transportation, Office of the Assistant Secretary for Research and Technology (USDOT/OST-R) under Grant No. 69A3551747126 through INSPIRE University Transportation Center (http://inspire-utc.mst.edu) at Missouri University of Science and Technology. The views, opinions, findings and conclusions reflected in this publication are solely those of the authors and do not represent the official policy or position of the USDOT/OST-R, or any State or other entity. J. Xiao has a significant financial interest in InnovBot LLC, a company involved in R&D and the commercialization of the technology.
References
Al-Nuaimy, W., Y. Huang, and A. Eriksen. 2001. “Automatic detection of hyperbolic signatures in ground-penetrating radar data.” In Vol. 4491 of Subsurface and surface sensing technologies and applications III, 327–335. Bellingham, WA: SPIE.
Al-Nuaimy, W., Y. Huang, M. Nakhkash, M. Fang, V. Nguyen, and A. Eriksen. 2000. “Automatic detection of buried utilities and solid objects with gpr using neural networks and pattern recognition.” J. Appl. Geophys. 43 (2–4): 157–165. https://doi.org/10.1016/S0926-9851(99)00055-5.
Benedetto, A. 2010. “Water content evaluation in unsaturated soil using gpr signal analysis in the frequency domain.” J. Appl. Geophys. 71 (1): 26–35. https://doi.org/10.1016/j.jappgeo.2010.03.001.
Benedetto, A., and F. Benedetto. 2011. “Remote sensing of soil moisture content by gpr signal processing in the frequency domain.” IEEE Sens. J. 11 (10): 2432–2441. https://doi.org/10.1109/JSEN.2011.2119478.
Chen, H., and A. G. Cohn. 2010. “Probabilistic robust hyperbola mixture model for interpreting ground penetrating radar data.” In Proc., 2010 Int. Joint Conf. on Neural Networks (IJCNN), 1–8. New York: IEEE.
Çiçek, Ö., A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger. 2016. “3d u-net: Learning dense volumetric segmentation from sparse annotation.” In Proc., Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, 424–432. Cham, Switzerland: Springer.
Demirci, S., E. Yigit, I. H. Eskidemir, and C. Ozdemir. 2012. “Ground penetrating radar imaging of water leaks from buried pipes based on back-projection method.” Ndt & E Int. 47 (Apr): 35–42. https://doi.org/10.1016/j.ndteint.2011.12.008.
Diamanti, N., and D. Redman. 2012. “Field observations and numerical models of GPR response from vertical pavement cracks.” J. Appl. Geophys. 81 (Jun): 106–116. https://doi.org/10.1016/j.jappgeo.2011.09.006.
Dolgiy, A., A. Dolgiy, and V. Zolotarev. 2006. “Optimal radius estimation for subsurface pipes detected by ground penetrating radar.” In Vol. 4 of Proc., 11th Int. Conf. on Ground Penetrating Radar, Columbus, Ohio, USA. New York: IEEE.
Dupont, E., M. B. Martin, A. Colburn, A. Sankar, J. Susskind, and Q. Shan. 2020. “Equivariant neural rendering.” In Proc., Int. Conf. on Machine Learning, PMLR, 2761–2770. New York: Proceedings of Machine Learning Research.
Fan, H., H. Su, and L. J. Guibas. 2017. “A point set generation network for 3d object reconstruction from a single image.” In Proc., IEEE Conf. on Computer Vision and Pattern Recognition, 605–613. New York: IEEE.
Feng, J., L. Yang, E. Hoxha, B. Jiang, and J. Xiao. 2022a. “Robotic inspection of underground utilities for construction survey using a ground penetrating radar.” J. Comput. Civ. Eng. 37 (1): 04022049. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001062.
Feng, J., L. Yang, E. Hoxha, D. Sanakov, S. Sotnikov, and J. Xiao. 2021a. “GPR-based model reconstruction system for underground utilities using gprnet.” In Proc., 2021 IEEE Int. Conf. on Robotics and Automation (ICRA), 845–851. New York: IEEE.
Feng, J., L. Yang, E. Hoxha, and J. Xiao. 2022b. “Improving 3d metric GPR imaging using automated data collection and learning-based processing.” IEEE Sens. J. 23 (5): 4527–4539. https://doi.org/10.1109/JSEN.2022.3164707.
Feng, J., L. Yang, H. Wang, Y. Tian, and J. Xiao. 2021b. “Subsurface pipes detection using DNN-based back projection on GPR data.” In Proc., IEEE/CVF Winter Conf. on Applications of Computer Vision, 266–275. New York: IEEE.
Fernandes, F. M., and J. C. Pais. 2017. “Laboratory observation of cracks in road pavements with GPR.” Constr. Build. Mater. 154 (Nov): 1130–1138. https://doi.org/10.1016/j.conbuildmat.2017.08.022.
Fontul, S., A. Paixão, M. Solla, and L. Pajewski. 2018. “Railway track condition assessment at network level by frequency domain analysis of GPR data.” Remote Sens. 10 (4): 559. https://doi.org/10.3390/rs10040559.
González-Huici, M. A., I. Catapano, and F. Soldovieri. 2014. “A comparative study of GPR reconstruction approaches for landmine detection.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7 (12): 4869–4878.
Grasmueck, M., and A. Novo. 2016. “3d GPR imaging of shallow plastic pipes, tree roots, and small objects.” In Proc., 2016 16th Int. Conf. on Ground Penetrating Radar (GPR), 1–6. New York: IEEE.
He, K., X. Zhang, S. Ren, and J. Sun. 2016. “Deep residual learning for image recognition.” In Proc., IEEE Conf. on Computer Vision and Pattern Recognition, 770–778. New York: IEEE.
Hou, F., W. Lei, S. Li, and J. Xi. 2021a. “Deep learning-based subsurface target detection from gpr scans.” IEEE Sens. J. 21 (6): 8161–8171. https://doi.org/10.1109/JSEN.2021.3050262.
Hou, F., W. Lei, S. Li, J. Xi, M. Xu, and J. Luo. 2021b. “Improved mask R-CNN with distance guided intersection over union for GPR signature detection and segmentation.” Autom. Constr. 121 (Jan): 103414. https://doi.org/10.1016/j.autcon.2020.103414.
Hu, D., J. Chen, and S. Li. 2022. “Reconstructing unseen spaces in collapsed structures for search and rescue via deep learning based radargram inversion.” Autom. Constr. 140 (Aug): 104380. https://doi.org/10.1016/j.autcon.2022.104380.
Kang, M.-S., N. Kim, S. B. Im, J.-J. Lee, and Y.-K. An. 2019. “3d gpr image-based ucnet for enhancing underground cavity detectability.” Remote Sens. 11 (21): 2545. https://doi.org/10.3390/rs11212545.
Khudoyarov, S., N. Kim, and J.-J. Lee. 2020. “Three-dimensional convolutional neural network–based underground object classification using three-dimensional ground penetrating radar data.” Struct. Health Monit. 19 (6): 1884–1893. https://doi.org/10.1177/1475921720902700.
Kilic, G., and L. Eren. 2018. “Neural network based inspection of voids and karst conduits in hydro–electric power station tunnels using GPR.” J. Appl. Geophys. 151 (Apr): 194–204. https://doi.org/10.1016/j.jappgeo.2018.02.026.
Kingma, D. P., and J. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted December 22, 2014. https://arxiv.org/abs/1412.6980.
Krysiński, L., and J. Sudyka. 2013. “GPR abilities in investigation of the pavement transversal cracks.” J. Appl. Geophys. 97 (Oct): 27–36. https://doi.org/10.1016/j.jappgeo.2013.03.010.
Lai, W.-L., and C.-S. Poon. 2012. “GPR data analysis in time-frequency domain.” In Proc., 2012 14th Int. Conf. on Ground Penetrating Radar (GPR), 362–366. New York: IEEE.
Lai, W. W., R. K. Chang, and J. F. Sham. 2017. “Detection and imaging of city’s underground void by GPR.” In Proc., 2017 9th Int. Workshop on Advanced Ground Penetrating Radar (IWAGPR), 1–6. New York: IEEE.
Lai, W. W., R. K. Chang, and J. F. Sham. 2018. “A blind test of nondestructive underground void detection by ground penetrating radar (GPR).” J. Appl. Geophys. 149 (Feb): 10–17. https://doi.org/10.1016/j.jappgeo.2017.12.010.
Lee, K., J. Zung, P. Li, V. Jain, and H. S. Seung. 2017. “Superhuman accuracy on the snemi3d connectomics challenge.” Preprint, submitted May 31, 2017. https://arxiv.org/abs/1706.00120.
Lei, W., F. Hou, J. Xi, Q. Tan, M. Xu, X. Jiang, G. Liu, and Q. Gu. 2019. “Automatic hyperbola detection and fitting in GPR B-scan image.” Autom. Constr. 106 (Oct): 102839. https://doi.org/10.1016/j.autcon.2019.102839.
Lei, W., J. Luo, F. Hou, L. Xu, R. Wang, and X. Jiang. 2020. “Underground cylindrical objects detection and diameter identification in GPR B-scans via the CNN-LSTM framework.” Electronics 9 (11): 1804. https://doi.org/10.3390/electronics9111804.
Li, H., C. Chou, L. Fan, B. Li, D. Wang, and D. Song. 2019. “Toward automatic subsurface pipeline mapping by fusing a ground-penetrating radar and a camera.” IEEE Trans. Autom. Sci. Eng. 17 (2): 722–734. https://doi.org/10.1109/TASE.2019.2941848.
Li, S., H. Cai, D. M. Abraham, and P. Mao. 2014. “Estimating features of underground utilities: Hybrid gpr/gps approach.” J. Comput. Civ. Eng. 30 (1): 04014108. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000443.
Li, S., H. Cai, and V. R. Kamat. 2015. “Uncertainty-aware geospatial system for mapping and visualizing underground utilities.” Autom. Constr. 53 (May): 105–119. https://doi.org/10.1016/j.autcon.2015.03.011.
Liu, T., A. Klotzsche, M. Pondkule, H. Vereecken, J. Van Der Kruk, and Y. Su. 2017. “Estimation of subsurface cylindrical object properties from gpr full-waveform inversion.” In Proc., 2017 9th Int. Workshop on Advanced Ground Penetrating Radar (IWAGPR), 1–4. New York: IEEE.
Lopera, O., N. Milisavljevie, D. Daniels, and B. Macq. 2007. “Time-frequency domain signature analysis of GPR data for landmine identification.” In Proc., 2007 4th Int. Workshop on, Advanced Ground Penetrating Radar, 159–162. New York: IEEE.
Lu, Y., and G. Lu. 2022. “3d modeling beneath ground: Plant root detection and reconstruction based on ground-penetrating radar.” In Proc., IEEE/CVF Winter Conf. on Applications of Computer Vision, 68–77. New York: IEEE.
Luo, T. X., W. W. Lai, R. K. Chang, and D. Goodman. 2019. “GPR imaging criteria.” J. Appl. Geophys. 165 (Jun): 37–48. https://doi.org/10.1016/j.jappgeo.2019.04.008.
Mohamadi, S., D. Lattanzi, and H. Azari. 2020. “Fusion and visualization of bridge deck nondestructive evaluation data via machine learning.” Front. Mater. 7 (Nov): 576918.
Murez, Z., T. van As, J. Bartolozzi, A. Sinha, V. Badrinarayanan, and A. Rabinovich. 2020. “Atlas: End-to-end 3d scene reconstruction from posed images.” In Proc., Computer Vision–ECCV 2020: 16th European Conf., Glasgow, UK, August 23–28, 2020, Proc., Part VII 16, 414–431. New York: Springer.
Paszke, A., et al. 2019. “Pytorch: An imperative style, high-performance deep learning library.” In Vol. 32 of Advances in neural information processing systems, 8026–8037. San Mateo, CA: Kaufmann.
Pereira, M., D. Burns, D. Orfeo, Y. Zhang, L. Jiao, D. Huston, and T. Xia. 2020. “3-d multistatic ground penetrating radar imaging for augmented reality visualization.” IEEE Trans. Geosci. Remote Sens. 58 (8): 5666–5675. https://doi.org/10.1109/TGRS.2020.2968208.
Pereira, M., Y. Zhang, D. Huston, and T. Xia. 2019a. “3-d sar imaging for multistatic gpr.” In Vol. 10980 of Image sensing technologies: Materials, devices, systems, and applications VI. Bellingham, WA: SPIE.
Pereira, M., Y. Zhang, D. Orfeo, D. Burns, D. Huston, and T. Xia. 2018. “3d tomography for multistatic gpr subsurface sensing.” In Vol. 10633 of Radar sensor technology XXII. International Society for Optics and Photonics. Bellingham, WA: SPIE.
Pereira, M., Y. Zhang, D. Orfeo, D. Burns, D. Huston, and T. Xia. 2019b. “3d tomographic image reconstruction for multistatic ground penetrating radar.” In Proc., 2019 IEEE Radar Conf. (RadarConf), 1–6. New York: IEEE.
Poljak, D., S. Sesnic, A. Susnjara, D. Paric, V. Doric, and S. Antonijevic. 2018. “Frequency domain and time domain analysis of the transient field radiated by GPR antenna.” In Proc., 2018 3rd Int. Conf. on Smart and Sustainable Technologies (SpliTech), 1–6. New York: IEEE.
Qin, H., X. Xie, J. A. Vrugt, K. Zeng, and G. Hong. 2016. “Underground structure defect detection and reconstruction using crosshole GPR and Bayesian waveform inversion.” Autom. Constr. 68 (Aug): 156–169. https://doi.org/10.1016/j.autcon.2016.03.011.
Rezatofighi, H., N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese. 2019. “Generalized intersection over union: A metric and a loss for bounding box regression.” In Proc., IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 658–666. New York: IEEE.
Ronneberger, O., P. Fischer, and T. Brox. 2015. “U-net: Convolutional networks for biomedical image segmentation.” In Proc., Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, 234–241. New York: Springer.
Shihab, S., and W. Al-Nuaimy. 2005. “Radius estimation for cylindrical objects detected by ground penetrating radar.” Subsurface Sens. Technol. Appl. 6 (2): 151–166. https://doi.org/10.1007/s11220-005-0004-1.
Soldovieri, F., R. Solimene, L. L. Monte, M. Bavusi, and A. Loperte. 2010. “Sparse reconstruction from GPR data with applications to rebar detection.” IEEE Trans. Instrum. Meas. 60 (3): 1070–1079. https://doi.org/10.1109/TIM.2010.2078310.
Sun, Z., and Y. Sun. 2019. “Automatic detection of retinal regions using fully convolutional networks for diagnosis of abnormal maculae in optical coherence tomography images.” J. Biomed. Opt. 24 (5): 056003.
Topczewski, L., F. M. Fernandes, P. J. Cruz, and P. B. Lourenço. 2007. “Practical implications of gpr investigation using 3d data reconstruction and transmission tomography.” J. Build. Appraisal 3 (1): 59–76. https://doi.org/10.1057/palgrave.jba.2950060.
Tsoflias, G. P., C. Perll, M. Baker, and M. W. Becker. 2015. “Cross-polarized gpr imaging of fracture flow channeling.” J. Earth Sci. 26 (6): 776–784. https://doi.org/10.1007/s12583-015-0612-1.
van Kempen, L., H. D. Nho, H. Sahli, G. Hislop, and T. Tang. 2004. “A comparison of GPR reconstruction techniques.” In Vol. 1 of Proc., 10th Int. Conf. on Grounds Penetrating Radar, 2004. GPR 2004, 345–348. New York: IEEE.
Wahab, W. A., J. Jaafar, I. M. Yassin, and M. R. Ibrahim. 2013. “Interpretation of ground penetrating radar (GPR) image for detecting and estimating buried pipes and cables.” In Proc., 2013 IEEE Int. Conf. on Control System, Computing and Engineering, 361–364. New York: IEEE.
Warren, C., A. Giannopoulos, and I. Giannakis. 2016. “GPRMAX: Open source software to simulate electromagnetic wave propagation for ground penetrating radar.” Comput. Phys. Commun. 209 (Dec): 163–170. https://doi.org/10.1016/j.cpc.2016.08.020.
Windsor, C., L. Capineri, P. Falorni, S. Matucci, and G. Borgioli. 2005a. “The estimation of buried pipe diameters using ground penetrating radar.” Insight Non-Destr. Test. Cond. Monit. 47 (7): 394–399. https://doi.org/10.1784/insi.2005.47.7.394.
Windsor, C. G., L. Capineri, and P. Falorni. 2005b. “The estimation of buried pipe diameters by generalized Hough transform of radar data.” Piers Online 1 (3): 345–349. https://doi.org/10.2529/PIERS041117130829.
Wu, Y., F. Shen, M. Zhang, Y. Miao, T. Wan, and D. Xu. 2022. “A novel FDTD-based 3-D RTM imaging method for GPR working on dispersive medium.” IEEE Trans. Geosci. Remote Sens. 60 (Jul): 1–13.
Wu, Z., and C. Liu. 1999. “An image reconstruction method using GPR data.” IEEE Trans. Geosci. Remote Sens. 37 (1): 327–334. https://doi.org/10.1109/36.739064.
Xie, X., J. Zhai, and B. Zhou. 2021. “Back-fill grouting quality evaluation of the shield tunnel using ground penetrating radar with bi-frequency back projection method.” Autom. Constr. 121 (Jan): 103435. https://doi.org/10.1016/j.autcon.2020.103435.
Zenone, T., G. Morelli, M. Teobaldelli, F. Fischanger, M. Matteucci, M. Sordini, A. Armani, C. Ferrè, T. Chiti, and G. Seufert. 2008. “Preliminary use of ground-penetrating radar and electrical resistivity tomography to study tree roots in pine forests and poplar plantations.” Funct. Plant Biol. 35 (10): 1047–1058. https://doi.org/10.1071/FP08062.
Zhang, H., O. Shan, G. Wang, J. Li, S. Wu, and F. Zhang. 2015. “Back-projection algorithm based on self-correlation for ground-penetrating radar imaging.” J. Appl. Remote Sens. 9 (1): 095059. https://doi.org/10.1117/1.JRS.9.095059.
Zhao, W., E. Forte, S. T. Levi, M. Pipan, and G. Tian. 2015. “Improved high-resolution GPR imaging and characterization of prehistoric archaeological features by means of attribute analysis.” J. Archaeol. Sci. 54 (Feb): 77–85. https://doi.org/10.1016/j.jas.2014.11.033.
Information & Authors
Information
Published In
Journal of Computing in Civil Engineering
Volume 37 • Issue 6 • November 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Feb 3, 2023
Accepted: Apr 26, 2023
Published online: Aug 7, 2023
Published in print: Nov 1, 2023
Discussion open until: Jan 7, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Communication systems
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction management
- Engineering fundamentals
- Equipment and machinery
- Geology
- Geotechnical engineering
- Geotechnical investigation
- Infrastructure
- Lifeline systems
- Models (by type)
- Neural networks
- Radar
- Subsurface environment
- Subsurface investigation
- Three-dimensional models
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.