Automatic Corrosive Environment Detection of RC Bridge Decks from Ground-Penetrating Radar Data Based on Deep Learning
Publication: Journal of Performance of Constructed Facilities
Volume 36, Issue 2
Abstract
Detecting the corrosive environment of reinforced concrete (RC) bridge decks is of critical importance for evaluating the reliability and safety of bridge structures. However, accurately and automatically detecting a corrosive environment with traditional methods is challenging. This paper proposes a method for the automatic corrosive environment detection of bridge decks from ground-penetrating radar (GPR) data based on the single-shot multibox detector (SSD) model. This method can be divided into three steps: data preprocessing, automatic rebar picking, and corrosive environment mapping. First, the GPR data are preprocessed to enhance the contrast of the hyperbolic feature in GPR B-scans. Then the rebars in the B-scan images are automatically picked up by the trained SSD model. Finally, the corrosive environment contour map of the bridge deck is generated with the rebar reflection amplitudes after depth correction. The SSD model was trained with 10,316 B-scan images and tested with 2,578 images. The B-scan image typically included three to five hyperbolas. A case study with GPR data from a tested bridge was employed to validate the feasibility of the proposed method. The results show that the accuracy of the automatic corrosive environment detection method can reach 98% and is considerably higher than that of commercial software methods.
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 that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This research work was supported by the National Natural Science Foundation of China (Grant Nos. 52050050, 51978128, and 51908104).
References
Barnes, C. L., J. F. Trottier, and D. Forgeron. 2008. “Improved concrete bridge deck evaluation using GPR by accounting for signal depth-amplitude effects.” NDT&E Int. 41 (6): 427–433. https://doi.org/10.1016/j.ndteint.2008.03.005.
Bralich, J., D. Reichman, L. M. Collins, and J. M. Malof. 2017. “Improving convolutional neural networks for buried target detection in ground-penetrating radar using transfer learning via pretraining.” In Vol. 10182 of Proc., Detection and Sensing of Mines, Explosive Objects, and Obscured Targets 22, 101820X. Anaheim, CA: SPIE. https://doi.org/10.1117/12.2263112.
Bungey, J., S. Millard, and M. Grantham. 2006. Testing of concrete in structures. 4th ed. Boca Raton, FL: CRC Press.
Dinh, K., N. Gucunski, J. Kim, and T. H. Duong. 2016. “Understanding depth-amplitude effects in assessment of GPR data from concrete bridge decks.” NDT&E Int. 83 (10): 48–58. https://doi.org/10.1016/j.ndteint.2016.06.004.
Dinh, K., T. Zayed, F. Romero, and A. Tarussov. 2015. “Method for analyzing time-series GPR data of concrete bridge decks.” J. Bridge Eng. 20 (6): 04014086. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000679.
Dou, Q., L. Wei, D. R. Magee, and A. G. Cohn. 2017. “Real-time hyperbola recognition and fitting in GPR data.” IEEE Trans. Geosci. Remote Sens. 55 (1): 51–62. https://doi.org/10.1109/TGRS.2016.2592679.
Goulias, D. G., S. Cafiso, A. Di Graziano, and S. G. Saremi. 2020. “Condition assessment of bridge decks through ground-penetrating radar in bridge management systems.” J. Perform. Constr. Facil. 34 (5): 04020100. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001507.
GSSI (Geophysical Survey Systems Inc.). 2017. RADAN 7 manual. Nashua, NH: GSSI.
Gucunski, N., S. Nazarian, A. Imani, and H. Azari. 2014. “Performance of NDT technologies in detection and characterization of reinforced concrete deck deterioration.” In Geo-Congress 2014 Technical Papers: Geo-Characterization and Modeling for Sustainability, 2436–2449. Reston, VA: ASCE. https://doi.org/10.1061/9780784413272.236.
Hasan, I., and N. Yazdani. 2016. “An experimental study for quantitative estimation of rebar corrosion in concrete using ground-penetrating radar.” J. Eng. 2016 (Jan): 1–8. https://doi.org/10.1155/2016/8536850.
Hing, C. L. C., and U. B. Halabe. 2010. “Nondestructive testing of GFRP bridge decks using ground-penetrating radar and infrared thermography.” J. Bridge Eng. 15 (4): 391–398. https://doi.org/10.1061/(ASCE)BE.1943-5592.0000066.
Hugenschmidt, J. 2010. “Ground-penetrating radar for the evaluation of reinforced concrete structures.” Non-Destr. Eval. Reinf. Concr. Struct. 2 (Jan): 317–333. https://doi.org/10.1533/9781845699604.2.317.
Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2017. “ImageNet classification with deep convolutional neural networks.” Commun. ACM 60 (6): 84–90. https://doi.org/10.1145/3065386.
Lai, W. L., T. Kind, and H. Wiggenhauser. 2010. “Detection of accelerated reinforcement corrosion in concrete by ground-penetrating radar.” In Proc., 13th Int. Conf. on Ground-penetrating Radar, 1–5. New York: IEEE. https://doi.org/10.1109/icgpr.2010.5550254.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Lee, K. L., and M. M. Mokji. 2014. “Automatic target detection in GPR images using histogram of oriented gradients (HOG).” In Proc., 2nd Int. Conf. on Electronic Design, 181–186. New York: IEEE. https://doi.org/10.1109/ICED.2014.7015795.
Liu, H., X. Huang, F. Han, J. Cui, B. F. Spencer, and X. Xie. 2019. “Hybrid polarimetric GPR calibration and elongated object orientation estimation.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12 (7): 1–5. https://doi.org/10.1109/JSTARS.2019.2895942.
Liu, H., C. Lina, J. Cuia, L. Fanb, X. Xie, and B. F. Spencerd. 2020. “Detection and localization of rebar in concrete by deep learning using ground-penetrating radar.” Autom. Constr. 118 (Oct): 103279. https://doi.org/10.1016/j.autcon.2020.103279.
Liu, W., D. Anguelov, D. Erhan, and C. Szegedy. 2016. “SSD: Single shot multiBox detector.” In Proc., 14th European Conf. on Comput. Vision, 21–37. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-46448-0.
Maas, C., and J. Schmalzl. 2013. “Using pattern recognition to automatically localize reflection hyperbolas in data from ground-penetrating radar.” Comput. Geosci. 58 (8): 116–125. https://doi.org/10.1016/j.cageo.2013.04.012.
Martino, N., K. Maser, R. Birken, and M. Wang. 2015. “Quantifying bridge deck corrosion using ground-penetrating radar.” Res. Nondestr. Eval. 27 (May): 112–124. https://doi.org/10.1080/09349847.2015.1067342.
Mertens, L., R. Persico, L. Matera, and S. Lambot. 2016. “Automated detection of reflection hyperbolas in complex GPR images with no a priori knowledge on the medium.” IEEE Trans. Geosci. Remote Sens. 54 (1): 580–596. https://doi.org/10.1109/TGRS.2015.2462727.
Noreen, T., and U. S. Khan. 2017. “Using pattern recognition with HOG to automatically detect reflection hyperbolas in ground-penetrating radar data.” In Proc., Int. Conf. on Electrical and Computing Technologies and Applications, 1–6. New York: IEEE. https://doi.org/10.1109/ICECTA.2017.8252064.
Pasolli, E., F. Melgani, and M. Donelli. 2009. “Automatic analysis of GPR images: A pattern recognition approach.” IEEE Trans. Geosci. Remote Sens. 47 (7): 2206–2217. https://doi.org/10.1109/TGRS.2009.2012701.
Pe’er, U., and J. G. Dy. 2017. “Automated target detection for geophysical applications.” IEEE Trans. Geosci. Remote Sens. 55 (3): 1563–1572. https://doi.org/10.1109/TGRS.2016.2627245.
Reichman, D., L. M. Collins, and J. M. Malof. 2017. “Some good practices for applying convolutional neural networks to buried threat detection in ground-penetrating radar.” In Proc., 9th Int. Workshop on Advanced Ground-penetrating Radar, 1–5. New York: IEEE. https://doi.org/10.1109/IWAGPR.2017.7996100.
Sakaguchi, R. T., K. D. Morton, L. M. Collins, and P. A. Torrione. 2015. “Recognizing subsurface target responses in ground-penetrating radar data using convolutional neural networks.” In Vol. 9454 of Proc., Detection and Sensing of Mines, Explosive Objects, and Obscured Targets 20, 94541A. Bellingham, WA: International Society for Optical Engineering. https://doi.org/10.1117/12.2177747.
Sun, H., S. Pashoutani, and J. Zhu. 2018. “Nondestructive evaluation of concrete bridge decks with automated acoustic scanning system and ground-penetrating radar.” Sensors 18 (6): 1955. https://doi.org/10.3390/s18061955.
Tarussov, A., M. Vandry, and A. De La Haza. 2013. “Condition assessment of concrete structures using a new analysis method: Ground-penetrating radar computer-assisted visual interpretation.” Constr. Build. Mater. 38 (1): 1246–1254. https://doi.org/10.1016/j.conbuildmat.2012.05.026.
Travassos, X. L., S. L. Avila, and N. Ida. 2018. “Artificial neural networks and machine learning techniques applied to ground-penetrating radar: A review.” Appl. Comput. Inf. 17 (2): 1–7. https://doi.org/10.1016/j.aci.2018.10.001.
Wei, X., and Y. Zhang. 2014. “Autofocusing techniques for GPR data from RC bridge decks.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7 (12): 4860–4868. https://doi.org/10.1109/JSTARS.2014.2321710.
Wiwatrojanagul, P., R. Sahamitmongkol, and S. Tangtermsirikul. 2017. “A new method to determine locations of rebars and estimate cover thickness of RC structures using GPR data.” Constr. Build. Mater. 140 (6): 257–273. https://doi.org/10.1016/j.conbuildmat.2017.02.126.
Zhou, F., Z. Chen, and H. Liu. 2018. “Simultaneous estimation of rebar diameter and cover thickness by a GPR-EMI dual sensor.” Sensors 18 (9): 2969. https://doi.org/10.3390/s18092969.
Information & Authors
Information
Published In
Journal of Performance of Constructed Facilities
Volume 36 • Issue 2 • April 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Sep 15, 2021
Accepted: Dec 8, 2021
Published online: Feb 14, 2022
Published in print: Apr 1, 2022
Discussion open until: Jul 14, 2022
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.
Cited by
- Yu-Chen Zhang, Yan-Liang Du, Ting-Hua Yi, Song-Han Zhang, Automatic Correction of Abnormal Ground Penetrating Radar Data for Concrete Bridge Deck Corrosion Assessment, Journal of Performance of Constructed Facilities, 10.1061/JPCFEV.CFENG-4719, 38, 5, (2024).
- Hai-En Tang, Ting-Hua Yi, Song-Han Zhang, Chong Li, Multidamage Identification in High-Resolution Concrete Bridge Component Imagery Based on Deep Learning, Journal of Performance of Constructed Facilities, 10.1061/JPCFEV.CFENG-4671, 38, 5, (2024).
- Yu-Chen Zhang, Yan-Liang Du, Ting-Hua Yi, Song-Han Zhang, Automatic Rebar Picking for Corrosion Assessment of RC Bridge Decks with Ground-Penetrating Radar Data, Journal of Performance of Constructed Facilities, 10.1061/JPCFEV.CFENG-4591, 38, 2, (2024).
- Md. Ashiqur Rahman, Lu Zhang, Kingsley Lau, Xuan Lv, Leveraging Bridge and Environmental Features to Analyze Coating Conditions of Steel Bridges in Florida Using Neural Network Models, Journal of Performance of Constructed Facilities, 10.1061/JPCFEV.CFENG-4502, 37, 6, (2023).
- Chi-Yun Liu, Jui-Sheng Chou, Bayesian-optimized deep learning model to segment deterioration patterns underneath bridge decks photographed by unmanned aerial vehicle, Automation in Construction, 10.1016/j.autcon.2022.104666, 146, (104666), (2023).
- Yang Zhang, Ka-Veng Yuen, Review of artificial intelligence-based bridge damage detection, Advances in Mechanical Engineering, 10.1177/16878132221122770, 14, 9, (168781322211227), (2022).
- Zhen Liu, Xingyu Gu, Hailu Yang, Lutai Wang, Yihan Chen, Danyu Wang, Novel YOLOv3 Model With Structure and Hyperparameter Optimization for Detection of Pavement Concealed Cracks in GPR Images, IEEE Transactions on Intelligent Transportation Systems, 10.1109/TITS.2022.3174626, 23, 11, (22258-22268), (2022).