Deep learning-based detection of tie bars in concrete pavement using ground penetrating radar

References

• Al-Qadi, I.L., and Lahouar, S, 2005. Measuring layer thicknesses with gpr - theory to practice. Construction and Building Materials, 19 (10), 763–772. Available from: <Go to ISI>://WOS:000231776500007.
   Web of Science ®Google Scholar
• Amer-Yahia, C., and Majidzadeh, T, 2014. Approach to identify misaligned dowel and tie bars in concrete pavements using ground penetrating radar. Case Studies in Nondestructive Testing and Evaluation, 2, 14–26.
   Google Scholar
• Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M, 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
   Google Scholar
• Bodla, N., et al., 2017. Soft-nms - improving object detection with one line of code. 2017 Ieee International Conference on Computer Vision (Iccv), 5562–5570 Available from: <Go to ISI>://WOS:000425498405068.
   Google Scholar
• Chen, R., et al., 2022. Detection of delamination and rebar debonding in concrete structures with ultrasonic sh-waveform tomography. Automation in Construction, 133, 104004.
   Web of Science ®Google Scholar
• Chen, D.H., Hong, F., and Yuan, J, 2012. Effect of tie bars on the field performance of full-depth repair on concrete pavement. Road Materials and Pavement Design, 13 (1), 12–25.
   Web of Science ®Google Scholar
• Chen, D.H., Won, M., and Hong, F, 2009. Investigation of settlement of a jointed concrete pavement. Journal of Performance of Constructed Facilities, 23 (6), 440–446. Available from: <Go to ISI>://WOS:000271829000009.
   Web of Science ®Google Scholar
• Cheng, R., et al., 2021. Multi-scale safety helmet detection based on sas-yolov3-tiny. Applied Sciences, 11 (8), 3652.
   Google Scholar
• Deng, J., et al., 2009. Imagenet: A large-scale hierarchical image databaseed.^eds. 2009 IEEE conference on computer vision and pattern recognitionIeee, 248–255.
   Google Scholar
• Di Mascio, P., et al., 2018. Design of the first Italian roundabout with jointed plain concrete pavement. Applied Sciences-Basel, 8 (2), Available from: <Go to ISI>://WOS:000427510300135.
   Web of Science ®Google Scholar
• Dinh, K., and Gucunski, N, 2021. Factors affecting the detectability of concrete delamination in gpr images. Construction and Building Materials, 274, Available from: <Go to ISI>://WOS:000614164100029.
   Web of Science ®Google Scholar
• Dinh, K., Gucunski, N., and Duong, T.H, 2018. An algorithm for automatic localization and detection of rebars from gpr data of concrete bridge decks. Automation in Construction, 89, 292–298. Available from: <Go to ISI>://WOS:000430777700024.
   Web of Science ®Google Scholar
• Everingham, M., et al., 2010. The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88 (2), 303–338. Available from: <Go to ISI>://WOS:000275955400009.
   Web of Science ®Google Scholar
• Feng, D., Wang, X., and Zhang, B, 2018. Specific evaluation of tunnel lining multi-defects by all-refined gpr simulation method using hybrid algorithm of fetd and fdtd. Construction and Building Materials, 185, 220–229.
   Web of Science ®Google Scholar
• Gao, J., et al., 2020. Autonomous pavement distress detection using ground penetrating radar and region-based deep learning. Measurement, 164, 108077.
   Web of Science ®Google Scholar
• Giannopoulos, A, 2005. Modelling ground penetrating radar by gprmax. Construction & Building Materials, 19 (10), 755–762.
   Web of Science ®Google Scholar
• Girshick, R., 2021. Fast r-cnned.^eds. Proceedings of the IEEE international conference on computer vision, 1440–1448.
   Google Scholar
• Guo, C., et al., 2021a. Improved yolov4-tiny network for real-time electronic component detection. Scientific Reports, 11 (1), 1–13.
   PubMed Web of Science ®Google Scholar
• Guo, L., et al., 2022. Anti-interference of a small-world spiking neural network against pulse noise. Applied Intelligence, 7 (1), 1–19.
   Web of Science ®Google Scholar
• Guo, F., Qian, Y., and Shi, Y, 2021b. Real-time railroad track components inspection based on the improved yolov4 framework. Automation in Construction, 125, 103596.
   Web of Science ®Google Scholar
• Ha, S., Choi, S., and Won, M.C, 2010. Behavior of tied multiple-lane Portland cement concrete pavement: effects of environmental loading and dowel bar use. Transportation Research Record, 2154 (1), 57–77.
   Google Scholar
• He, K.M., et al., 2015. Spatial pyramid pooling in deep convolutional networks for visual recognition. Ieee Transactions on Pattern Analysis and Machine Intelligence, 37 (9), 1904–1916. Available from: <Go to ISI>://WOS:000359216600013.
   PubMed Web of Science ®Google Scholar
• He, K.M., et al., 2016. Deep residual learning for image recognition. 2016 Ieee Conference on Computer Vision and Pattern Recognition (Cvpr), 770–778 Available from: <Go to ISI>://WOS:000400012300083.
   Google Scholar
• Ioffe, S., and Szegedy, C., 2015. Batch normalization: accelerating deep network training by reducing internal covariate shifted.^eds. International conference on machine learningPMLR, 448–456.
   Google Scholar
• Jiang, Z., et al., 2020. Real-time object detection method based on improved yolov4-tiny. arXiv preprint arXiv:2011.04244.
   Google Scholar
• Jiang, Y.Q., Pang, D.D., and Li, C.D., 2021. A deep learning approach for fast detection and classification of concrete damage. Automation in Construction, 128, Available from: <Go to ISI>://WOS:000659521000001.
   Web of Science ®Google Scholar
• Joshaghani, A., and Shokrabadi, M, 2021. Ground penetrating radar (gpr) applications in concrete pavements. International Journal of Pavement Engineering, Available from: <Go to ISI>://WOS:000675149700001.
   Google Scholar
• Kumar, B, 2021. Response of instrumented concrete pavement slabs to vehicular loads. International Journal of Pavement Engineering, 23 (13), 4554–4560.
   Web of Science ®Google Scholar
• Lei, W.T., et al., 2019. Automatic hyperbola detection and fitting in gpr b-scan image. Automation in Construction, 106, Available from: <Go to ISI>://WOS:000488136600022.
   Web of Science ®Google Scholar
• Li, S., et al., 2021. Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm. Construction and Building Materials, 273, 121949.
   Web of Science ®Google Scholar
• Li, M, 2021. Modified multifractional gaussian noise and its application. Physica Scripta, 96 (12), 125002.
   Web of Science ®Google Scholar
• Lin, T.-Y., et al., 2014. Microsoft coco: common objects in contexted.^eds. European conference on computer visionSpringer, 740–755.
   Google Scholar
• Lin, T.-Y., et al., 2017a. Feature pyramid networks for object detectioned.^eds. Proceedings of the IEEE conference on computer vision and pattern recognition, 2117–2125.
   Google Scholar
• Lin, T.-Y., et al., 2017b. Focal loss for dense object detectioned.^eds. Proceedings of the IEEE international conference on computer vision, 2980–2988.
   Google Scholar
• Liu, W., et al., 2016. Ssd: Single shot multibox detector. Computer Vision - Eccv 2016, Pt I, 9905, 21–37 Available from: <Go to ISI>://WOS:000389382700002.
   Google Scholar
• Liu, S., et al., 2018. Path aggregation network for instance segmentation. 2018 Ieee/Cvf Conference on Computer Vision and Pattern Recognition (Cvpr), 8759–8768 Available from: <Go to ISI>://WOS:000457843608096.
   Google Scholar
• Liu, G., et al., 2020a. Yolo-tomato: a robust algorithm for tomato detection based on yolov3. Sensors, 20 (7), 2145.
   PubMed Web of Science ®Google Scholar
• Liu, H., et al., 2020b. Detection and localization of rebar in concrete by deep learning using ground penetrating radar. Automation in Construction, 118, 103279.
   Web of Science ®Google Scholar
• Liu, J., et al., 2020c. Automated pavement crack detection and segmentation based on two-step convolutional neural network. Computer-Aided Civil and Infrastructure Engineering, 35 (11), 1291–1305.
   Web of Science ®Google Scholar
• Maas, A.L., Hannun, A.Y., and Ng, A.Y., 2013. Rectifier nonlinearities improve neural network acoustic modelsed.^eds. Proc. icmlCiteseer, 3.
   Google Scholar
• Mccabe, T., et al., 2021. Early detection of honeycombs in concrete pavement using gpr. Journal of Performance of Constructed Facilities, 35 (1), Available from: <Go to ISI>://WOS:000641763700013.
   Web of Science ®Google Scholar
• Mechbal, Z., and Khamlichi, A, 2017. Determination of concrete rebars characteristics by enhanced post-processing of gpr scan raw data. Ndt & E International, 89, 30–39. Available from: <Go to ISI>://WOS:000402219800004.
   Web of Science ®Google Scholar
• Misra, D, 2019. Mish: A self regularized non-monotonic activation function. arXiv preprint arXiv:1908.08681.
   Google Scholar
• Park, S., et al., 2021. Improvement of gpr-based rebar diameter estimation using yolo-v3. Remote Sensing, 13 (10), Available from: <Go to ISI>://WOS:000662630300001.
   Web of Science ®Google Scholar
• Rasol, M.A., et al., 2020. Gpr laboratory tests and numerical models to characterize cracks in cement concrete specimens, exemplifying damage in rigid pavement. Measurement, 158, Available from: <Go to ISI>://WOS:000524745700034.
   Web of Science ®Google Scholar
• Redmon, J., et al., 2016. You only look once: unified, real-time object detection. IEEE.
   Google Scholar
• Redmon, J., and Farhadi, A, 2017. Yolo, 9000, Better, faster, stronger. 30th Ieee Conference on Computer Vision and Pattern Recognition (Cvpr 2017), 6517–6525 Available from: <Go to ISI>://WOS:000418371406065.
   Google Scholar
• Redmon, J., and Farhadi, A, 2018. Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767.
   Google Scholar
• Ren, S.Q., et al., 2017. Faster r-cnn: towards real-time object detection with region proposal networks. Ieee Transactions on Pattern Analysis and Machine Intelligence, 39 (6), 1137–1149. Available from: <Go to ISI>://WOS:000401091200007.
   PubMed Web of Science ®Google Scholar
• Soldovieri, F., et al., 2011. Sparse reconstruction from gpr data with applications to rebar detection. IEEE Transactions on Instrumentation and Measurement, 60 (3), 1070–1079.
   Web of Science ®Google Scholar
• Strange, A., 2013. Analysis of time interpolation for enhanced resolution gpr dataed.^eds. 2013 7th International Workshop on Advanced Ground Penetrating RadarIEEE, 1–5.
   Google Scholar
• Stryk, J., Matula, R., and Pospisil, K, 2013. Possibilities of ground penetrating radar usage within acceptance tests of rigid pavements. Journal of Applied Geophysics, 97, 11–26.
   Web of Science ®Google Scholar
• Sutskever, I., et al., 2013. On the importance of initialization and momentum in deep learninged.^eds. International conference on machine learningPMLR, 1139–1147.
   Google Scholar
• Taflove, A., and Brodwin, M.E, 1975. Numerical solution of steady-state electromagnetic scattering problems using the time-dependent Maxwell's equations. IEEE Transactions on Microwave Theory and Techniques, 23 (8), 623–630.
   Web of Science ®Google Scholar
• Tong, Z., et al., 2020b. Pavement-distress detection using ground-penetrating radar and network in networks. Construction and Building Materials, 233, Available from: <Go to ISI>://WOS:000513295100066.
   Web of Science ®Google Scholar
• Tong, Z., Gao, J., and Yuan, D.D, 2020a. Advances of deep learning applications in ground-penetrating radar: A survey. Construction and Building Materials, 258, Available from: <Go to ISI>://WOS:000571168700016.
   Web of Science ®Google Scholar
• Tong, Z., Gao, J., and Zhang, H.T, 2018. Innovative method for recognizing subgrade defects based on a convolutional neural network. Construction and Building Materials, 169, 69–82. Available from: <Go to ISI>://WOS:000430994700008.
   Web of Science ®Google Scholar
• Utsi, V., 2010. How many points per scan?ed.^eds. Proceedings of the XIII Internarional Conference on Ground Penetrating RadarIEEE, 1–4.
   Google Scholar
• Wang, C.Y., et al., 2020. Cspnet: a new backbone that can enhance learning capability of cnned.^eds. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
   Google Scholar
• Wang, S., and Al-Qadi, I.L, 2021. Impact and removal of ground-penetrating radar vibration on continuous asphalt concrete pavement density prediction. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–14.
   Web of Science ®Google Scholar
• Wang, S.Q., Al-Qadi, I.L., and Cao, Q.Q, 2020b. Factors impacting monitoring asphalt pavement density by ground penetrating radar. Ndt & E International, 115, Available from: <Go to ISI>://WOS:000571492200003.
   Web of Science ®Google Scholar
• Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M., 2021. Scaled-yolov4: scaling cross stage partial networked.^eds. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13029–13038.
   Google Scholar
• Wang, Y.H., Cui, G.Y., and Xu, J, 2020c. Semi-automatic detection of buried rebar in gpr data using a genetic algorithm. Automation in Construction, 114, Available from: <Go to ISI>://WOS:000526785800018.
   Web of Science ®Google Scholar
• Warren, C., Giannopoulos, A., and Giannakis, I, 2016. Gprmax: open source software to simulate electromagnetic wave propagation for ground penetrating radar. Computer Physics Communications, 209, 163–170.
   Web of Science ®Google Scholar
• Watanabe, T., et al., 2014. Evaluation of corrosion-induced crack and rebar corrosion by ultrasonic testing. Construction and Building Materials, 67, 197–201.
   Web of Science ®Google Scholar
• Wiwatrojanagul, P., Sahamitmongkol, R., and Tangtermsirikul, S, 2018. A method to detect lap splice in reinforced concrete using a combination of covermeter and gpr. Construction and Building Materials, 173, 481–494. Available from: <Go to ISI>://WOS:000432645200049.
   Web of Science ®Google Scholar
• Xiang, Z.M., Ou, G., and Rashidi, A, 2020. Integrated approach to simultaneously determine 3d location and size of rebar in gpr data. Journal of Performance of Constructed Facilities, 34 (5), Available from: <Go to ISI>://WOS:000609479700017.
   Web of Science ®Google Scholar
• Xiang, Z.M., Ou, G., and Rashidi, A, 2021. Robust cascaded frequency filters to recognize rebar in gpr data with complex signal interference. Automation in Construction, 124, Available from: <Go to ISI>://WOS:000623401700004.
   PubMed Web of Science ®Google Scholar
• Xiong, X.T., et al., 2021. Estimation of density and moisture content in asphalt mixture based on dielectric property. Construction and Building Materials, 298, Available from: <Go to ISI>://WOS:000686011700011.
   Web of Science ®Google Scholar
• Yee, K, 1966. Numerical solution of initial boundary value problems involving Maxwell's equations in isotropic media. IEEE Transactions on Antennas and Propagation, 14 (3), 302–307.
   Google Scholar
• Yun, S., et al., 2019. Cutmix: regularization strategy to train strong classifiers with localizable features. 2019 Ieee/Cvf International Conference on Computer Vision (Iccv 2019), 6022–6031 Available from: <Go to ISI>://WOS:000548549201014.
   Google Scholar
• Zakria, Z., et al., 2022. Multiscale and direction target detecting in remote sensing images via modified yolo-v4. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 1039–1048.
   Web of Science ®Google Scholar
• Zeiler, M.D, 2012. Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701.
   Google Scholar
• Zheng, Z., et al., 2020. Distance-iou loss: faster and better learning for bounding box regressioned.^eds. Proceedings of the AAAI Conference on Artificial Intelligence, 12993–13000.
   Google Scholar
• Zhu, J.Q., et al., 2022. Pavement distress detection using convolutional neural networks with images captured via uav. Automation in Construction, 133. Available from: <Go to ISI>://WOS:000707873800002.
   Web of Science ®Google Scholar