Deep Learning Applications for Analysing Concrete Surface Cracks

Abstract

Deep learning is transforming concrete crack analysis into civil engineering, enabling automated, accurate, and scalable detection essential for maintaining infrastructure like bridges, buildings, and roads. Traditional methods, relying on manual inspections or basic image processing, are often time-consuming and prone to errors, especially over large or complex structures. This review explores the application of deep learning models—especially CNNs and advanced architectures like U-Net, Mask R-CNN, and DeepLab—in detecting, segmenting, and quantifying cracks with precision. It also addresses innovations such as transfer learning to overcome data limitations and the use of mobile and drone-based platforms for field inspections. Challenges remain, including model generalization and computational demands. This paper concludes with future directions for enhancing real-time crack analysis through unsupervised learning, multi-modal data, and edge AI solutions, underscoring deep learning’s transformative potential for infrastructure safety and maintenance.

References

[1] ASKAR MK, AL-KAMAKI YA, FERHADI R, MAJEED HK. Cracks in concrete structures causes and treatments: A review. Journal of Duhok University. 2023 Dec 22;26(2):148-65.

[2] Munawar HS, Hammad AW, Haddad A, Soares CA, Waller ST. Image-based crack detection methods: A review. Infrastructures. 2021 Aug 14;6(8):115.

[3] Chen H, Kim S, Hardie JM, Thirumalaraju P, Gharpure S, Rostamian S, Udayakumar S, Lei Q, Cho G, Kanakasabapathy MK, Shafiee H. Deep learning-assisted sensitive detection of fentanyl using a bubbling-microchip. Lab on a Chip. 2022;22(23):4531-40.

[4] Nafissi N, Heiranizadeh N, Shirinzadeh-Dastgiri A, Vakili-Ojarood M, Naseri A, Danaei M, Saberi A, Aghasipour M, Shiri A, Yeganegi M, Rahmani A. The Application of Artificial Intelligence in Breast Cancer. EJMO. 2024;8(3):235-44.

[5] Zhou SK, Greenspan H, Shen D, editors. Deep learning for medical image analysis. Academic Press; 2023 Nov 23.

[6] Orouskhani M, Zhu C, Rostamian S, Zadeh FS, Shafiei M, Orouskhani Y. Alzheimer's disease detection from structural MRI using conditional deep triplet network. Neuroscience Informatics. 2022 Dec 1;2(4):100066.

[7] Tashakkori A, Erfanibehrouz N, Mirshekari S, Sodagartojgi A, Gupta V. Enhancing stock market prediction accuracy with recurrent deep learning models: A case study on the CAC40 index. World Journal of Advanced Research and Reviews. 2024;23(1):2309-1.

[8] Nandi B, Jana S, Das KP. Machine learning-based approaches for financial market prediction: A comprehensive review. Journal of AppliedMath. 2023 Aug 28;1(2):134-.

[9] Tashakkori A, Talebzadeh M, Salboukh F, Deshmukh L. Forecasting Gold Prices with MLP Neural Networks: A Machine Learning Approach. International Journal of Science and Engineering Applications (IJSEA). 2024;13:13-20.

[10] Neshenko N, Bou‐Harb E, Furht B, Behara R. Machine learning and user interface for cyber risk management of water infrastructure. Risk Analysis. 2024 Apr;44(4):833-49.

[11] Pinto A, Herrera LC, Donoso Y, Gutierrez JA. Survey on intrusion detection systems based on machine learning techniques for the protection of critical infrastructure. Sensors. 2023 Feb 22;23(5):2415.

[12] DAbubakr M, Rady M, Badran K, Mahfouz SY. Application of deep learning in damage classification of reinforced concrete bridges. Ain Shams engineering journal. 2024 Jan 1;15(1):102297.

[13] Bharadiya J. Convolutional neural networks for image classification. International Journal of Innovative Science and Research Technology. 2023;8(5):673-7.

[14] Abbasi H, Afrazeh F, Ghasemi Y, Ghasemi F. A Shallow Review of Artificial Intelligence Applications in Brain Disease: Stroke, Alzheimer's, and Aneurysm. International Journal of Applied Data Science in Engineering and Health. 2024 Oct 5;1(2):32-43.

[15] Amjoud AB, Amrouch M. Object detection using deep learning, CNNs and vision transformers: A review. IEEE Access. 2023 Apr 10;11:35479-516.

[16] Kaur R, Singh S. A comprehensive review of object detection with deep learning. Digital Signal Processing. 2023 Jan 1;132:103812.

[17] Hadinata PN, Simanta D, Eddy L, Nagai K. Multiclass Segmentation of Concrete Surface Damages Using U-Net and DeepLabV3+. Applied Sciences. 2023 Feb 13;13(4):2398.

[18] Abbasi H, Orouskhani M, Asgari S, Zadeh SS. Automatic brain ischemic stroke segmentation with deep learning: A review. Neuroscience Informatics. 2023 Sep 22:100145.

[19] Dadfarin A, Maleki YS, Esna-Ashari M. The effects of freeze–thaw cycles on the UCS of the CTS specimens reinforced with DTY fibers. Construction and Building Materials. 2023 Aug 22;393:132055.

[20] Hasani A, Dorafshan S. Transforming construction? Evaluation of the state of structural 3D concrete printing in research and practice. Construction and Building Materials. 2024 Aug 9;438:137027.

[21] Saffarian I, Atefatdoost GR, Hosseini SA, Shahryari L. Experimental and numerical research on the behavior of steel-fiber-reinforced-concrete columns with GFRP rebars under axial loading. Structural Engineering and Mechanics, An Int'l Journal. 2023 May;86(3):399-415.

[22] Saffarian I, Atefatdoost GR, Hosseini SA, Shahryari L. Experimental research on the behavior of circular SFRC columns reinforced longitudinally by GFRP rebars. Computers and Concrete. 2023;31(6):513-25.

[23] Arabi P, Zadeh SS. The environmental impact of anti-icing materials on asphalt surfaces (commonly used anti-icing agents). Environ Eng. 2023;9:1-4.

[24] Joushideh N, Zadeh SS, Bahrami B, Mahmoudabadi NS. Pseudo-static slope stability analysis and numerical settlement assessment of rubble mound breakwater under hydrodynamic conditions. World Journal of Advanced Research and Reviews. 2023;19(2):273-87.

[25] Zadeh SS, Khorshidi M, Kooban F. Concrete Surface Crack Detection with Convolutional-based Deep Learning Models. arXiv preprint arXiv:2401.07124. 2024 Jan 13.

[26] Kirthiga R, Elavenil S. A survey on crack detection in concrete surface using image processing and machine learning. Journal of Building Pathology and Rehabilitation. 2024 Jun;9(1):15.

[27] Dong X, Liu Y, Dai J. Concrete Surface Crack Detection Algorithm Based on Improved YOLOv8. Sensors. 2024 Aug 14;24(16):5252.

[28] Mirbod M, Shoar M. Intelligent concrete surface cracks detection using computer vision, pattern recognition, and artificial neural networks. Procedia Computer Science. 2023 Jan 1;217:52-61.

[29] Zhang J, Cai YY, Yang D, Yuan Y, He WY, Wang YJ. MobileNetV3-BLS: A broad learning approach for automatic concrete surface crack detection. Construction and Building Materials. 2023 Aug 15;392:131941.

[30] Laxman KC, Tabassum N, Ai L, Cole C, Ziehl P. Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning. Construction and Building Materials. 2023 Mar 17;370:130709.

[31] Tabernik D, Šuc M, Skočaj D. Automated detection and segmentation of cracks in concrete surfaces using joined segmentation and classification deep neural network. Construction and Building Materials. 2023 Dec 8;408:133582.

[32] Manjunatha P, Masri SF, Nakano A, Wellford LC. CrackDenseLinkNet: a deep convolutional neural network for semantic segmentation of cracks on concrete surface images. Structural Health Monitoring. 2024 Mar;23(2):796-817.

[33] Mishra A, Gangisetti G, Eftekhar Azam Y, Khazanchi D. Weakly supervised crack segmentation using crack attention networks on concrete structures. Structural Health Monitoring. 2024:14759217241228150.

[34] Shamsabadi EA, Erfani SM, Xu C, Dias-da-Costa D. Efficient semi-supervised surface crack segmentation with small datasets based on consistency regularisation and pseudo-labelling. Automation in Construction. 2024 Feb 1;158:105181.s

[35] Zhou K, Lei D, Chun PJ, She Z, He J, Du W, Hong M. Evaluation of BFRP strengthening and repairing effects on concrete beams using DIC and YOLO-v5 object detection algorithm. Construction and Building Materials. 2024 Jan 12;411:134594.

[36] Ye G, Qu J, Tao J, Dai W, Mao Y, Jin Q. Autonomous surface crack identification of concrete structures based on the YOLOv7 algorithm. Journal of Building Engineering. 2023 Aug 15;73:106688.

[37] Zhang Y, Ni YQ, Jia X, Wang YW. Identification of concrete surface damage based on probabilistic deep learning of images. Automation in Construction. 2023 Dec 1;156:105141.

[38] Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence. 2017 Apr 27;40(4):834-48.

[39] Bae H, An YK. Computer vision-based statistical crack quantification for concrete structures. Measurement. 2023 Apr 1;211:112632.

[40] Gonthina M, Chamata R, Duppalapudi J, Lute V. Deep CNN-based concrete cracks identification and quantification using image processing techniques. Asian Journal of Civil Engineering. 2023 Apr;24(3):727-40.

[41] Xu G, Yue Q, Liu X. Real-time monitoring of concrete crack based on deep learning algorithms and image processing techniques. Advanced Engineering Informatics. 2023 Oct 1;58:102214.

[42] Feng L, Qian X. Enhanced real-time crack monitoring and updating in welded structural components with limited measurement data. Mechanical Systems and Signal Processing. 2023 Sep 1;198:110403.