Field Validation of Deep-Learning-Based Ground Penetrating Radar Image Analysis for Advancing Subsurface Distress Detection

Abstract

This research introduces an innovative method for detecting subsurface cracks within pavements by leveraging ground penetrating radar (GPR) technology in conjunction with advanced deep learning techniques. Its primary aim is to significantly improve the accuracy and efficiency of pavement assessment, particularly for operational and maintenance purposes. The proposed model, GPR-YOLOR (You Only Learn One Representation), extends the YOLOR framework and incorporates a region of interest within the top pavement layer to detect subsurface cracks. While the model can be trained with annotated data, the main challenge lies in validating results in the field because of the inability to visually inspect subsurface conditions and the high cost associated with direct coring. To overcome this challenge, we propose an alternative approach that utilizes the co-occurrence of surface cracks as pseudo labels, allowing for easy verification. To ensure that surface cracks correspond to subsurface cracks, the focus is exclusively on transverse cracks that develop in a bottom-up manner, such as fatigue and reflective cracks. Through this methodology, our GPR-YOLOR model achieves an F1 score of 0.72, with a precision of 0.76 and a recall of 0.68. The results from field validation underscore the effectiveness of the GPR-YOLOR model in accurately identifying subsurface cracks, highlighting its practical significance in conducting field condition assessments.

Keywords

infrastructure pavements pavement condition evaluation data detection ground-penetrating radar

Get full access to this article

View all access options for this article.

References

Diamanti

Redman

Giannopoulos

A Study of GPR Vertical Crack Responses in Pavement Using Field Data and Numerical Modelling. Proc., XIII International Conference on Ground Penetrating Radar, Lecce, Italy, IEEE, New York, 2010, pp. 1–6. https://doi.org/10.1109/ICGPR.2010.5550224.

Solla

Lagüela

González-Jorge

Arias

Approach to Identify Cracking in Asphalt Pavement Using GPR and Infrared Thermographic Methods: Preliminary Findings. NDT & E International, Vol. 62, 2014, pp. 55–65.

Szymczyk

Non-Destructive Building Investigation Through Analysis of GPR Signal by S-Transform. Automation in Construction, Vol. 55, 2015, pp. 35–46.

Zeng

Shen

GPR Detection of Several Common Subsurface Voids Inside Dikes and Dams. Engineering Geology, Vol. 111, No. 1–4, 2010, pp. 31–42.

Zhou

Jiang

Liang

Automatic Detection Algorithm for Expressway Subgrade Diseases Based on SVM. Zhongguo Gonglu Xuebao/China Journal of Highway and Transport, Vol. 26, No. 2, 2013, pp. 42–47.

Yanqing

Xiaoming

Wei

Shunzhi

Improvement on Recognition Method of Void beneath Slab Based on Nondestructive Testing Technologies. Sustainable Construction Materials 2012, 2013, pp. 77–91. https://ascelibrary.org/doi/10.1061/9780784412671.0007.

Tosti

Benedetto

Pavement Pumping Prediction Using Ground Penetrating Radar. Procedia-Social and Behavioral Sciences, Vol. 53, 2012, pp. 1044–1053.

Barat

Ducottet

String Representations and Distances in Deep Convolutional Neural Networks for Image Classification. Pattern Recognition, Vol. 54, 2016, pp. 104–115.

Shi

Bai

Yao

Script Identification in the Wild via Discriminative Convolutional Neural Network. Pattern Recognition, Vol. 52, 2016, pp. 448–458.

10.

Leng

Xiong

A 3D Shape Retrieval Framework for 3D Smart Cities. Frontiers of Computer Science in China, Vol. 4, No. 3, 2010, pp. 394–404.

11.

Cha

Choi

Suh

Mahmoudkhani

Büyüköztürk

. Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types. Computer-Aided Civil and Infrastructure Engineering, Vol. 33, No. 9, 2018, pp. 731–747.

12.

Liu

Sha

Tong

Gao

Autonomous Microscopic Bunch Inspection Using Region-Based Deep Learning for Evaluating Graphite Powder Dispersion. Construction and Building Materials, Vol. 173, 2018, pp. 525–539.

13.

Tong

Gao

Sha

Convolutional Neural Network for Asphalt Pavement Surface Texture Analysis. Computer-Aided Civil and Infrastructure Engineering, Vol. 33, No. 12, 2018, pp. 1056–1072.

14.

Tong

Gao

Zhang

Innovation for Evaluating Aggregate Angularity Based Upon 3D Convolutional Neural Network. Construction and Building Materials, Vol. 155, 2017, pp. 919–929.

15.

Cha

Choi

Büyüköztürk

. Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks. Computer-Aided Civil and Infrastructure Engineering, Vol. 32, No. 5, 2017, pp. 361–378.

16.

Sha

A-m

Zheng

Gao

Recognition and Measurement of Pavement Disasters Based on Convolutional Neural Networks. China Journal of Highway and Transport, Vol. 31, No. 1, 2018, pp. 1–10.

17.

Tong

Gao

Zhang

Recognition, Location, Measurement, and 3D Reconstruction of Concealed Cracks Using Convolutional Neural Networks. Construction and Building Materials, Vol. 146, 2017, pp. 775–787.

18.

Tong

Gao

Zhang

Innovative Method for Recognizing Subgrade Defects Based on a Convolutional Neural Network. Construction and Building Materials, Vol. 169, 2018, pp. 69–82.

19.

Wang

Ding

Liang

Detection of Urban Expansion and Land Surface Temperature Change Using Multi-Temporal Landsat Images. Resources, Conservation and Recycling, Vol. 128, 2018, pp. 526–534.

20.

Beckman

Polyzois

Cha

Deep Learning-Based Automatic Volumetric Damage Quantification Using Depth Camera. Automation in Construction, Vol. 99, 2019, pp. 114–124.

21.

Hinton

Deng

Dahl

Mohamed

Jaitly

Sainath

Deep Neural Networks for Acoustic Modeling in Speech Recognition. IEEE Signal Processing Magazine, Vol. 29, No. 6, 2012, pp. 82–97.

22.

Abdel-Hamid

Mohamed

A. R.

Jiang

Penn

Applying Convolutional Neural Networks Concepts to Hybrid NN-HMM Model for Speech Recognition. Proc., IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, New York, 2012, pp. 4277–4280.

23.

Krizhevsky

Sutskever

Hinton

G. E.

ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, Vol. 25, 2012, pp. 1097–1105.

24.

Hinton

G. E.

Srivastava

Krizhevsky

Sutskever

Salakhutdinov

R. R.

Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors. arXiv preprint arXiv:1207.0580, 2012.

25.

Abdelmawla

Yang

Kim

Subsurface Anomaly Detection Utilizing Synthetic GPR Images and Deep Learning Model. Geomechanics and Engineering, Vol. 33, No. 2, 2023, pp. 203–209. https://doi.org/10.12989/gae.2023.33.2.203.

26.

Robert

F. L.

Kandhal

P. S.

Brown

Lee

D.-Y.

Kennedy

Performance/Distress in HMA: Hot Mix Asphalt Materials, Mixture Design and Construction, 2nd ed. National Asphalt Pavement Association, Lanham, MD, 1996.

27.

National Center for Pavement Preservation (U.S.), and Colorado Department of Transportation. Colorado DOT Distress Manual for HMA and PCC Pavements: Pavement Preservation. Okemos, MI; National Center for Pavement Preservation, Denver, Colo.; Colorado Department of Transportation, 2004. http://hermes.cde.state.co.us/drupal/islandora/object/co:22047/datastream/OBJ/view.

28.

Zuiderveld

Contrast Limited Adaptive Histogram Equalization. Academic Press, Cambridge, MA, 1994, pp. 474–485.