Distance Insensitive Concrete Crack Detection with Controlled Blurriness Using a Convolutional Neural Network

Document Type : Research Papers

Authors

1 M.Sc., School of Civil Engineering, University Teknologi Malaysia, Johor, Malaysia.

2 Assistant Professor, School of Civil Engineering, University Teknologi Malaysia, Johor, Malaysia.

3 Associate Professor, School of Civil Engineering, University Teknologi Malaysia, Johor, Malaysia.

Abstract

Crack detection is one of the critical tasks in health monitoring and inspection of civil engineering structures. The existence of major cracks may have detrimental effects on the integrity and performance of structures that need full consideration. Recent research into crack identification has shown an increasing interest in vision-based automated techniques, employing deep-learning computational methods such as Convolutional Neural Networks (CNNs). However, the wide range of real-world situations (e.g. camera or subject motion, misfocus, mist, and fog) can significantly compromise the accuracy of CNN-based crack identification due to a mismatched dataset in training and testing. Therefore, this study aims to establish an intelligent identification model using deep CNNs to automatically detect concrete cracks from real-world images. Moreover, the efficiency of the algorithm in identifying cracks based on blurred images in the training and validation dataset was investigated. The original dataset is replicated into various blurriness levels and split into eight different crack image sub-datasets. CNN models were trained and crack identification was carried out using different levels of image blurriness. The classification performance of the trained CNN was assessed using the concrete crack image dataset taken around Universiti Teknologi Malaysia. Sensitivity studies were also conducted to investigate the efficiency of the CNN method to identify damage under various image parameters. The results showed that the subset with the combination of sharp and slight blurriness level (blurriness Level 1) reached the highest training accuracy of 98.20%, and the network trained with blurriness Level 1 alone had the best accuracy, precision, and F1 score performance over eight training subsets. Moreover, the robustness of the networks was examined and verified under four different situations, which are; lighting, crack width, colour structures, and camera shooting angle conditions. It was observed that the presence of blurred images in the training dataset can enhance the CNN crack detection performance while high shooting angle and uneven illumination has a negative effect on the accuracy of the proposed CNN.

Keywords

References

Abdulkareem, M., Bakhary, N., Vafaei, M., Noor, N.M. and Padil, K.H. (2018). "Non-probabilistic wavelet method to consider uncertainties in structural damage detection", Journal of Sound and Vibration, 433(27 October), 77-98, https://doi.org/hdl.handle.net/11250/238284.
Abudallah Habib, I., Wan Mohtar, W.H.M., Muftah Shahot, K., El-shafie, A. and Abd Manan, T.S. (2021). "Bridge failure prevention: An overview of self-protected pier as flow altering countermeasures for scour protection", Civil Engineering Infrastructures Journal, 54(1), 1-22, https://doi.org/10.22059/CEIJ.2020.292296.1627.
Atha, D.J. and Jahanshahi, M.R. (2018). "Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection", Structural Health Monitoring, 17(5), 1110-11128, https://doi.org/10.1177/1475921717737051.
Cha, Y.J., Choi, W. and Büyüköztürk, O. (2017). "Deep learning-based crack damage detection using convolutional neural networks", Computer-Aided Civil and Infrastructure Engineering, 32(5), 361-78, https://doi.org/10.1111/mice.12263.
Cha, Y.J., Choi, W., Suh, G., Mahmoudkhani, S. and Büyüköztürk, O. (2018). "Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types", Computer-Aided Civil and Infrastructure Engineering, 33(9), 731-747, https://doi.org/10.1111/mice.12334.
Chen, F.C. and Jahanshahi, M.R. (2020). "ARF-crack: Rotation invariant deep fully convolutional network for pixel-level crack detection", Machine Vision and Applications, 31(6), 1-12, https://doi.org/10.1007/s00138-020-01098-x.
Ciresan, D.C., Meier, U., Masci, J., Gambardella, L.M. and Schmidhuber, J. (2011). "Flexible, high performance convolutional neural networks for image classification", Twenty Second International Joint Conference on Artificial Intelligence, Catalonia, Spain, https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-210.
Dash, R., Sa, P. K., and Majhi, B. (2009). "RBFN based motion blur parameter estimation", International Conference on Advanced Computer Control, 327-331, IEEE, Singapore, https://doi.org/10.1109/ICACC.2009.98.
Delatte, N. (2009). Failure, distress and repair of concrete structures, Elsevier, https://doi.org/10.1533/9781845697037.
Deng, L., Chu, H.H., Shi, P., Wang, W. and Kong, X. (2020). "Region-based CNN method with deformable modules for visually classifying concrete cracks", Applied Sciences, 10(7), 2528, https://doi.org/10.3390/app10072528.
Dorafshan, S. and Maguire, M. (2018). "Bridge inspection: Human performance, unmanned aerial systems and automation", Journal of Civil Structural Health Monitoring, 8(July), 443-476.
Dorafshan, S., Thomas, R.J. and Maguire, M. (2018). "Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete", Construction and Building Materials, 186(20  October), 1031-1045, https://doi.org/10.1007/s13349-018-0285-4.
Fan, Y., Zhao, Q., Ni, S., Rui, T., Ma, S. and Pang, N. (2018). "Crack detection based on the mesoscale geometric features for visual concrete bridge inspection", Journal of Electronic Imaging, 27(5), 053011, https://doi.org/10.1117/1.JEI.27.5.053011.
Fankhauser, N., Kalberer, N., Müller, F., Leles, C.R., Schimmel, M. and Srinivasan, M. (2020). "Comparison of smartphone‐camera and conventional flatbed scanner images for analytical evaluation of chewing function", Journal of oral rehabilitation, 47(12), 1496-502, https://doi.org/10.1111/joor.13094.
Han, X., Thomasson, J.A., Bagnall, G.C., Pugh, N.A., Horne, D.W., Rooney, W.L., Jung, J., Chang, A., Molambo, L., Popescu, S.C., Gates, I.T. and Cope, D.A. (2018). "Measurement and calibration of plant-height from fixed-wing UAV images", Sensors, 18(12), 4092, https://doi.org/10.3390/s18124092.
Jang, K., Kim, N., and An, Y.-K. (2019). "Deep learning–based autonomous concrete crack evaluation through hybrid image scanning", Structural Health Monitoring, 18(5-6), 1722-1737, https://doi.org/10.3390/s18124092.
Kim, B. and Cho, S. (2018). "Automated vision-based detection of cracks on concrete surfaces using a deep learning technique", Sensors, 18(10), 3452, https://doi.org/10.3390/s18103452.
Li, S., Zhao, X. and Zhou, G. (2019). "Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network", Computer-Aided Civil and Infrastructure Engineering, 34(7), 616-34, https://doi.org/10.1111/mice.12433.
Li, Y., Zhao, W., Zhang, X. and Zhou, O. (2018). "A two-stage crack detection method for concrete bridges using Convolutional Neural Networks", IEICE Transactioons on Information and Systems, 101(12), 3249-3252, https://doi.org/10.1587/transinf.2018EDL8150.
Protopapadakis, E., Voulodimos, A., Doulamis, A., Doulamis, N. and Stathaki, T. (2019). "Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing", Applied intelligence, 49(2), 2793-2806, https://doi.org/10.1007/s10489-018-01396-y.
Ratnam, M.M., Ooi, B.Y. and Yen, K.S. (2019). "Novel moiré‐based crack monitoring system with smartphone interface and cloud processing", Structural Control and Health Monitoring, 26(10), e2420, https://doi.org/10.1002/stc.2420.
Ryu, P.-M. (2018). "Predicting the unemployment rate using social media analysis", Journal of Information Processing Systems, 14(4), 904-915, https://doi.org/10.3745/JIPS.04.0079.
Shen, L., Fang, R., Yao, Y., Geng, X. and Wu, D. (2018). "No-reference stereoscopic image quality assessment based on image distortion and stereo perceptual information", IEEE Transactions on Emerging Topics in Computational Intelligence, 3(1), 59-72, https://doi.org/10.1109/TETCI.2018.2804885.
Sieberth, T., Wackrow, R., and Chandler, J. (2013). "Automatic isolation of blurred images from UAV image sequences", International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Rostock, Germany.
Sieberth, T., Wackrow, R. and Chandler, J. (2015). "UAV image blur-its influence and ways to correct it", The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Toronto, Canada, https://doi.org/10.5194/isprsarchives-XL-1-W4-33-2015
Wang, Y., Fang, Z. and Hong, H. (2019). "Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China", Science of The Total Environment, 666(20 May), 975-93, https://doi.org/10.1016/j.scitotenv.2019.02.263.
Yang, J. and Byun, H. (2007). "Illumination compensation algorithm using eigenspaces transformation for facial images", In: Gagalowicz, A., Philips, W. (eds.), Computer Vision/Computer Graphics Collaboration Techniques (MIRAGE 2007), Lecture Notes in Computer Science, Vol. 4418, Springer, Berlin, Heidelberg, https://doi.org/10.1007/978-3-540-71457-6_18.
Ye, X.-W., Dong, C.-Z. and Liu, T. (2016). "A review of machine vision-based structural health monitoring: methodologies and applications", Journal of Sensors, 2016, Article ID 7013039, https://doi.org/10.1155/2016/7103039.
Zhang, Y., Sun, X., Loh, K.J., Su, W., Xue, Z. and Zhao, X. (2020). "Autonomous bolt loosening detection using deep learning", Structural Health Monitoring, 19(1), 105-22, https://doi.org/10.1177/1475921719837509.
Zhou, S. and Song, W. (2021). "Deep learning-based roadway crack classification with heterogeneous image data fusion", Structural Health Monitoring, 20(3), 1274-1293, https://doi.org/10.1177/1475921720948434.
Civil Engineering Infrastructures Journal
Volume 56, Issue 1
June 2023
Pages 117-136

Files

History

  • Receive Date: 21 November 2021
  • Revise Date: 16 February 2022
  • Accept Date: 27 February 2022

Share

How to cite

Statistics