journal article·2026-07-10Open access

A Method for Detecting Multiple Types of Defects in Concrete Dams Based on an Improved YOLOv12 Model

Wenhao Xu, Wenjie Zhang, Bo Xu

Applied Sciences· Volume 16· Issue 14

Abstract

Accurate detection and characterization of surface defects in concrete dams is vital for ensuring safe operation. To address the limitations of existing research focused solely on cracks and the challenges traditional convolutional networks face in adapting to deformation and multiscale features, this study introduces DCN-YOLO, a deformable convolution-augmented framework for the simultaneous detection and classification of multiple defect types from UAV-acquired imagery. The model outputs bounding box localizations and categorical labels. Based on YOLOv12, this proposed model integrates DCNv4 deformable convolutions with the C3k2 module. By leveraging adaptive sampling offsets and dynamic modulation, the proposed model enhances geometric modeling for irregular defects, improving the detection of small and medium defects while achieving an acceptable trade-off in inference efficiency. To address multiple defect coexistence, we adopt Binary Cross-Entropy (BCE) loss to decouple classification and localization, improving training stability in multi-label scenarios. A Multi-defects dataset was created using UAV images, and performance was validated on the CrackSeg public dataset. The proposed model achieved 77.4% ± 0.2% overall precision under complex conditions, exceeding the YOLOv12l baseline by 7.1% and improving mAP50-95 by 4.2%. It demonstrated competitive performance in detecting cracks, aggregate exposure, and construction joints, thereby providing a potentially robust and efficient approach for intelligent inspection of concrete dam surface defects.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Infrastructure Maintenance and Monitoring · Dam Engineering and Safety · Advanced Neural Network Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

College of Hydraulic Science and Engineering, Yangzhou University, Yangzhou 225009, China

Funding

Open Research Fund Program of State Key Laboratory of Water Disaster Prevention

References (67)

Show source-provided references
1. A new dam structural response estimation paradigm powered by deep learning and transfer learning techniques10.1177/14759217211009780 ↗
2. A machine vision-based intelligent segmentation method for dam underwater cracks using swarm optimization algorithm and deep learning10.1111/mice.13343 ↗
3. A technical review of hydro-project development in China10.1016/J.ENG.2016.03.008 ↗
4. ACI Committee 207 (2007). Report on Thermal and Volume Change Effects on Cracking of Mass Concrete (ACI 207.2R-07), American Concrete Institute.
5. fib (2013). fib Model Code for Concrete Structures 2010, Ernst & Sohn.10.1002/9783433604090 ↗
6. Deep active sequential lea4rning of stress evolution in early-age concrete informed by thermo-chemo-mechanical modelling10.1016/j.engappai.2026.114985 ↗
7. Creep and shrinkage prediction model for analysis and design of concrete structures: Model B3
8. An integrated underwater structural multi-defects automatic identification and quantification framework for hydraulic tunnel via machine vision and deep learning10.1177/14759217221122316 ↗
9. Automated crack evaluation of a high-rise bridge pier using a ring-type climbing robot10.1111/mice.12550 ↗
10. Damage detection of tunnel based on the high-density cross-sectional curvature obtained using strain data from BOTDA sensors10.1016/j.ymssp.2021.107728 ↗
11. Stability monitoring of surrounding rock mass on a forked tunnel using both strain gauges and FBG sensors10.1016/j.measurement.2019.107449 ↗
12. Liang, J., Chen, B., Shao, C., Li, J., and Wu, B. (2020). Time reverse modeling of damage detection in underwater concrete beams using piezoelectric intelligent modules. Sensors, 20.10.3390/s20247318 ↗
13. Data-driven crack behavior anomaly identification method for concrete dams in long-term service using offline and online change point detection10.1007/s13349-021-00520-w ↗
14. Real-time assessment of surface cracks in concrete structures using integrated deep neural networks with autonomous unmanned aerial vehicle10.1016/j.engappai.2023.107537 ↗
15. Lightweight deep learning for real-time road distress detection on mobile devices10.1038/s41467-025-59516-5 ↗
16. UAV based sensing and imaging technologies for power system detection, monitoring and inspection: A review
17. Framework for automated UAS-based structural condition assessment of bridges10.1016/j.autcon.2018.10.006 ↗
18. Vision-based deformation monitoring of large scale structures using Unmanned Aerial Systems10.2749/222137814814070343 ↗
19. Precision UAV image-to-BIM registration through contour-based matching for concrete dam structural health monitoring10.1016/j.autcon.2025.106536 ↗
20. Structural health monitoring and inspection of dams based on UAV photogrammetry with image 3D reconstruction10.1016/j.autcon.2021.103832 ↗
21. Underwater dam crack image generation based on unsupervised image-to-image translation10.1016/j.autcon.2024.105430 ↗
22. Key technologies for intelligent construction and smart operation and maintenance of large-scale hydraulic tunnels10.26599/JIC.2025.9180102 ↗
23. Villarino, A., Valenzuela, H., Antón, N., Domínguez, M., and Cubillos, X.C.M. (2025). UAV applications for monitoring and management of civil infrastructures. Infrastructures, 10.10.3390/infrastructures10050106 ↗
24. Deep learning for cross-region streamflow and flood forecasting at a global scale
25. Machine learning for crack detection: Review and model performance comparison10.1061/(ASCE)CP.1943-5487.0000918 ↗
26. FCN attention enhancing asphalt pavement crack detection through attention mechanisms and fully convolutional networks10.1038/s41598-025-92971-0 ↗
27. Fu, D., Su, C., Wang, W., and Yuan, R. (2022). Deep learning based lithology classification of drill core images. PLoS ONE, 17.10.1371/journal.pone.0270826 ↗
28. Physics-based analysis and data-driven detection of artificial intelligence–generated surface crack images for civil infrastructure monitoring10.1061/JCCEE5.CPENG-6910 ↗
29. Automated damage index estimation of reinforced concrete columns for post-earthquake evaluations10.1061/(ASCE)ST.1943-541X.0001200 ↗
30. NB-CNN: Deep learning-based crack detection using convolutional neural network and Naïve Bayes data fusion10.1109/TIE.2017.2764844 ↗
31. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete10.1016/j.conbuildmat.2018.08.011 ↗
32. Bhowmick, S., Nagarajaiah, S., and Veeraraghavan, A. (2020). Vision and deep learning-based algorithms to detect and quantify cracks on concrete surfaces from UAV videos. Sensors, 20.10.3390/s20216299 ↗
33. Vision-based quantification of stiffness degradation in reinforced concrete shear walls using graph-based surface crack features and machine learning10.1061/JSENDH.STENG-15932 ↗
34. A deep residual neural network framework with transfer learning for concrete dams patch-level crack classification and weakly-supervised localization10.1016/j.measurement.2021.110641 ↗
35. MOD-YOLO: Rethinking the YOLO architecture at the level of feature information and applying it to crack detection10.1016/j.eswa.2023.121346 ↗
36. Lightweight and high-performance object detector and tracking model for concrete surface defect detection10.1016/j.engappai.2025.111968 ↗
37. An improved YOLOv10 algorithm for automated damage detection of glass curtain-walls in high-rise buildings10.1016/j.jobe.2025.111812 ↗
38. Automated bridge surface crack detection and segmentation using computer vision-based deep learning model10.1016/j.engappai.2022.105225 ↗
39. Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024). DETRs beat YOLOs on real-time object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR52733.2024.01605 ↗
40. Tian, Y., Ye, Q., and Doermann, D. (2025). YOLOv12: Attention-centric real-time object detectors. arXiv.
41. Predictive equations for drift ratio and damage assessment of RC shear walls using surface crack patterns10.1016/j.engstruct.2019.04.018 ↗
42. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
43. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2016.91 ↗
44. Redmon, J., and Farhadi, A. (2017). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2017.690 ↗
45. Wang, Z., Men, S., Bai, Y., Yuan, Y., Wang, J., Wang, K., and Zhang, L. (2024). Improved small object detection algorithm CRL-YOLOv5. Sensors, 24.10.20944/preprints202408.1218.v1 ↗
46. CSP-Net: Common spatial pattern empowered neural networks for EEG-based motor imagery classification10.1016/j.knosys.2024.112668 ↗
47. A text detection algorithm for image of student exercises based on CTPN and enhanced YOLOv310.1109/ACCESS.2020.3025221 ↗
48. Deep Learning-based Severity Classification of Concrete Cracks using YOLOv8 for Structural Health Analysis
49. Improvement of Dam Crack Detection Algorithm for YOLOv910.1049/ipr2.70124 ↗
50. Mayya, A.M., and Alkayem, N.F. (2024). Enhance the concrete crack classification based on a novel multi-stage YOLOV10-ViT framework. Sensors, 24.10.3390/s24248095 ↗
51. He, L., Zhou, Y., Liu, L., and Ma, J. (2024). Research and application of YOLOv11-based object segmentation in intelligent recognition at construction sites. Buildings, 14.10.3390/buildings14123777 ↗
52. Katharopoulos, A., Vyas, A., Pappas, N., and Fleuret, F. (2020). Transformers are rnns: Fast autoregressive transformers with linear attention. International Conference on Machine Learning, PMLR.
53. Xie, E., Chen, J., Chen, J., Cai, H., Tang, H., Lin, Y., and Han, S. (2025). SANA: Efficient high-resolution text-to-image synthesis with linear diffusion transformers. The Thirteenth International Conference on Learning Representations, Curran Associates, Inc.
54. Nyströmformer: A nyström-based algorithm for approximating self-attention10.1609/aaai.v35i16.17664 ↗
55. Bhojanapalli, S., Yun, C., Rawat, A.S., Reddi, S., and Kumar, S. (2020). Low-rank bottleneck in multi-head attention models. International Conference on Machine Learning, PMLR.
56. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR52729.2023.00721 ↗
57. Transformers in medical imaging: A survey10.1016/j.media.2023.102802 ↗
58. Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017). Deformable convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, IEEE.10.1109/ICCV.2017.89 ↗
59. Zhu, X., Hu, H., Lin, S., and Dai, J. (2019). Deformable convnets v2: More deformable, better results. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2019.00953 ↗
60. Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., and Li, H. (2023). Internimage: Exploring large-scale vision foundation models with deformable convolutions. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR52729.2023.01385 ↗
61. Xiong, Y., Li, Z., Chen, Y., Wang, F., Zhu, X., Luo, J., Wang, W., Lu, T., Li, H., and Qiao, Y. (2024). Efficient deformable convnets: Rethinking dynamic and sparse operator for vision applications. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR52733.2024.00540 ↗
62. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection
63. YOLO-RACE: Reassembly and convolutional block attention for enhanced dense object detection10.1007/s10044-025-01471-4 ↗
64. Advanced registration method of UAV photogrammetry point clouds with BIM for 3D localization in concrete dams10.1016/j.aei.2024.102978 ↗
65. Shaker, A., Wasim, S.T., Khan, S., Gall, J., and Khan, F.S. (2025). GroupMamba: Efficient group-based visual state space model. Proceedings of the Computer Vision and Pattern Recognition Conference, IEEE.10.1109/CVPR52734.2025.01389 ↗
66. Zhu, J., Chen, X., He, K., LeCun, Y., and Liu, Z. (2025). Transformers without normalization. Proceedings of the Computer Vision and Pattern Recognition Conference, IEEE.10.1109/CVPR52734.2025.01388 ↗
67. Real-time high-resolution neural network with semantic guidance for crack segmentation10.1016/j.autcon.2023.105112 ↗