A STUDY OF THE INTELLIGENT RECOGNITION OF CONCRETE-STRUCTURE CRACKS BASED ON YOLOv7 AND C2E-Net
Abstract
Cracks, a common problem in concrete structures, severely compromise their safety and reliability. Accurate and efficient crack identification across diverse environmental conditions is pivotal for ensuring the safe operation and health monitoring of buildings. Accordingly, this paper innovatively proposes a novel intelligent crack-recognition model for concrete structures by integrating YOLOv7 and C2E-Net. First, crack features are extracted via the CA, ELG, and CCF modules of C2E-Net. These features are then inputted into an enhanced YOLOv7 model for fusion, which improves the recognition capability of tiny cracks. Additionally, the Inner-CIOU loss is introduced to optimize small-target detection, addressing the issue that traditional loss functions struggle to accurately identify small targets such as tiny cracks. Following the model’s refinement, we carry out ablation experiments. These experiments aim to assess the contribution of each functional module in the model’s structure and to uncover how the internal components work together. Finally, to validate the model’s performance, this paper selects SSD, Faster-RCNN, and Ghost-YOLO as contrast models and employs multiple evaluation metrics, including the Dice coefficient, IoU, detection accuracy, recall rate, and F1 score, for comprehensive analysis. The experimental results demonstrate that the C2E-Net-YOLOv7 model for concrete-structure-crack intelligent recognition performs exceptionally well during both the training and testing phases, with a Dice coefficient of 0.83, IoU of 0.81, detection accuracy of 91 %, recall rate of 89 %, and F1 score of 0.91. Compared to the traditional SSD model, the Dice coefficient increases by 50.91 %, IoU by 88.37 %, and detection accuracy by 59.65 %; relative to the Ghost-YOLO model, the Dice coefficient improves by 9.21 %, IoU by 22.73 %, and detection accuracy by 5.81 %. The experiments indicate that the YOLOv7 model with the C2E-Net module introduced achieves performance improvements in concrete-structure crack-detection tasks, breaking through the bottlenecks of traditional models and demonstrating remarkable superiority and effectiveness. This model offers an efficient and accurate method for intelligent crack recognition, helping to detect safety hazards promptly and ensuring the long-term stability and safety of buildings.
References
[1] M. Pal, P. Palevičius, M. Landauskas, U. Orinaitė, I. Timofejeva, M. Ragulskis, An overview of challenges associated with automatic detection of concrete cracks in the presence of shadows, Applied Sciences 11 (2021) 11396.
[2] P. Prasanna, K.J. Dana, N. Gucunski, B.B. Basily, H.M. La, R.S. Lim, H. Parvardeh, Automated crack detection on concrete bridges, IEEE Transactions on Automation Science and Engineering 13 (2014) 591–599.
[3] D. Ai, F. Mo, Y. Han, J. Wen, Automated identification of compressive stress and damage in concrete specimen using convolutional neural network learned electromechanical admittance, Engineering Structures 259 (2022) 114176.
[4] P. Palevičius, M. Pal, M. Landauskas, U. Orinaitė, I. Timofejeva, M. Ragulskis, Automatic detection of cracks on concrete surfaces in the presence of shadows, Sensors 22 (2022) 3662.
[5] S.E. Park, S.-H. Eem, H. Jeon, Concrete crack detection and quantification using deep learning and structured light, Construction and Building Materials 252 (2020) 119096.
[6] B. Kim, S. Cho, Automated vision-based detection of cracks on concrete surfaces using a deep learning technique, Sensors 18 (2018) 3452.
[7] J.C. Babu, M.S. Kumar, P. Jayagopal, V.E. Sathishkumar, S. Rajendran, S. Kumar, A. Karthick, A.M. Mahseena, IoT‐Based Intelligent System for Internal Crack Detection in Building Blocks, Journal of Nanomaterials 2022 (2022) 3947760. https://doi.org/10.1155/2022/3947760.
[8] Y. Luo, C. Liu, D. Mazlan, S.S.N. Kumar, Sustainable thermoelectric energy harvesting in fly ash bamboo fiber reinforced concrete for smart infrastructure, Energy and Buildings 343 (2025) 115927. https://doi.org/10.1016/j.enbuild.2025.115927.
[9] X. Cui, Q. Wang, J. Dai, S. Li, C. Xie, J. Wang, Pixel-level intelligent recognition of concrete cracks based on DRACNN, Materials Letters 306 (2022) 130867.
[10] C.V. Dung, Autonomous concrete crack detection using deep fully convolutional neural network, Automation in Construction 99 (2019) 52–58.
[11] R. Fu, H. Xu, Z. Wang, L. Shen, M. Cao, T. Liu, D. Novak, Enhanced intelligent identification of concrete cracks using multi-layered image preprocessing-aided convolutional neural networks, Sensors 20 (2020) 2021.
[12] Y. Luo, M.M. Yussof, L. Zhang, Study of thermal conductivity of constituent materials for electrically heated bridge decks, Construction and Building Materials 453 (2024) 139122. https://doi.org/10.1016/j.conbuildmat.2024.139122.
[13] Y. Luo, Y. Chen, Y. Yu, Mechanical and impermeability properties of bamboo fiber reinforced concrete before and after wet-dry cycling, Structures 73 (2025) 108363. https://doi.org/10.1016/j.istruc.2025.108363.
[14] Y. Luo, H. Liu, Thermoelectric power generation in concrete: A study on influential material and structural factors, Energy and Buildings 328 (2025) 115159. https://doi.org/10.1016/j.enbuild.2024.115159.
[15] H. Jin, H. Xu, C. Cai, L. Chen, T. Wang, L. Shen, Z. Wang, T. Chen, T. Ngo, Experimental investigation and model analysis of uniaxial compressive behavior, micro properties and sustainability of fiber-reinforced concrete designed by cost-efficiency fibers, Innov. Infrastruct. Solut. 10 (2025) 19. https://doi.org/10.1007/s41062-024-01801-1.
[16] H. Li, Y. Wei, K. Meng, L. Zhao, B. Zhu, B. Wei, Mechanical properties and stress-strain relationship of surface-treated bamboo fiber reinforced lightweight aggregate concrete, Construction and Building Materials 424 (2024) 135914.
[17] X. Han, Z. Zhao, L. Chen, X. Hu, Y. Tian, C. Zhai, L. Wang, X. Huang, Structural damage-causing concrete cracking detection based on a deep-learning method, Construction and Building Materials 337 (2022) 127562.
[18] K. Hu, Y. Ling, J. Liu, Image recognition technology for bituminous concrete reservoir panel cracks based on deep learning, PloS One 20 (2025) e0318550.
[19] Z. Huo, X. Wu, T. Cheng, Crack recognition and defect detection of assembly building constructions for intelligent construction, Journal of Measurements in Engineering 12 (2024) 485–501.
[20] Y. Liu, X. Huang, T. Xiao, Y. Hong, Q. Pu, X. Wen, Machine Vision Method for Crack Detection and Pattern Recognition in UHPC Prestressed Beams, J. Struct. Eng. 151 (2025) 04024219. https://doi.org/10.1061/JSENDH.STENG-13396.
[21] D. Ma, H. Fang, B. Xue, F. Wang, M.A. Msekh, C.L. Chan, Intelligent detection model based on a fully convolutional neural network for pavement cracks, Computer Modeling in Engineering & Sciences 123 (2020) 1267–1291.
[22] M. Mirbod, M. Shoar, Intelligent concrete surface cracks detection using computer vision, pattern recognition, and artificial neural networks, Procedia Computer Science 217 (2023) 52–61.
[23] M.Z. Naser, A. Seitllari, Concrete under fire: an assessment through intelligent pattern recognition, Engineering with Computers 36 (2020) 1915–1928. https://doi.org/10.1007/s00366-019-00805-1.
[24] H. Zhong, L. Shuai, D. Deng, Research on concrete structure damage detection based on piezoelectric sensing technology and morphological fractal method, Scientific Reports 15 (2025) 26604.
[25] J. Zhu, J. Song, Weakly supervised network based intelligent identification of cracks in asphalt concrete bridge deck, Alexandria Engineering Journal 59 (2020) 1307–1317.
[26] Y. Zhu, H. Tang, Automatic damage detection and diagnosis for hydraulic structures using drones and artificial intelligence techniques, Remote Sensing 15 (2023) 615.
[27] Y. Yu, M. Rashidi, B. Samali, M. Mohammadi, T.N. Nguyen, X. Zhou, Crack detection of concrete structures using deep convolutional neural networks optimized by enhanced chicken swarm algorithm, Structural Health Monitoring 21 (2022) 2244–2263. https://doi.org/10.1177/14759217211053546.
[28] X. Zhang, Z. Luo, J. Ji, Y. Sun, H. Tang, Y. Li, Intelligent Surface Cracks Detection in Bridges Using Deep Neural Network, Int. J. Str. Stab. Dyn. 24 (2024) 2450046. https://doi.org/10.1142/S0219455424500469.
[29] M. Zheng, Z. Lei, K. Zhang, Intelligent detection of building cracks based on deep learning, Image and Vision Computing 103 (2020) 103987.
[30] Z. Yang, Q. Chen, X. Li, H. Chen, Z. Wang, R. Huang, Q. Kong, Crack identification in concrete structures using implantable sensors, Measurement 202 (2022) 111780.
[31] Y. Yao, S.-T.E. Tung, B. Glisic, Crack detection and characterization techniques-An overview: CRACK DETECTION AND CHARACTERIZATION TECHNIQUES-AN OVERVIEW, Struct. Control Health Monit. 21 (2014) 1387–1413. https://doi.org/10.1002/stc.1655.
[32] X.-W. Ye, T. Jin, P.-Y. Chen, Structural crack detection using deep learning–based fully convolutional networks, Advances in Structural Engineering 22 (2019) 3412–3419. https://doi.org/10.1177/1369433219836292.
[33] G. Song, H. Gu, Y.-L. Mo, Smart aggregates: multi-functional sensors for concrete structures—a tutorial and areview, Smart Materials and Structures 17 (2008) 033001.
[34] R.A. Swarna, M.M. Hossain, M.R. Khatun, M.M. Rahman, A. Munir, Concrete crack detection and segregation: a feature fusion, crack isolation, and explainable AI-based approach, Journal of Imaging 10 (2024) 215.
[35] R. Wang, R.-Q. Chen, X.-X. Guo, J.-X. Liu, H.-Y. Yu, Automatic recognition system for concrete cracks with support vector machine based on crack features, Scientific Reports 14 (2024) 20057.
[36] Z. Qi, D. Liu, J. Zhang, J. Chen, Micro-concrete crack detection of underwater structures based on convolutional neural network, Machine Vision and Applications 33 (2022) 74. https://doi.org/10.1007/s00138-022-01327-5.
[37] P. Wu, A. Liu, J. Fu, X. Ye, Y. Zhao, Autonomous surface crack identification of concrete structures based on an improved one-stage object detection algorithm, Engineering Structures 272 (2022) 114962.
