Intelligent Detection of Underwater Defects in Concrete Dams Based on YOLOv8s-UEC
Source abstract
Abstract
This study proposes a concrete dam underwater apparent defect detection algorithm named YOLOv8s-UEC for intelligent identification of underwater defects. Due to the scarcity of existing images of underwater concrete defects, this study establishes a dataset of underwater defect images by manually constructing defective concrete walls for the training of defect detection networks. For the defect feature ambiguity that exists in underwater defects, the ConvNeXt Block module and Efficient-RepGFPN structure are introduced to enhance the feature extraction capability of the network, and the P2 detection layer is fused to enhance the detection capability of small-size defects such as cracks. The results show that the mean average precision (mAP0.5 and mAP0.5:0.95) of the improved algorithm are increased by 1.4% and 5.8%, and it exhibits good robustness and considerable detection effect for underwater defects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · 3D Surveying and Cultural Heritage · Concrete Corrosion and Durability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
China Institute of Water Resources and Hydropower Research, Beijing 100048, China
School of Infrastructure Engineering, Dalian University of Technology, Dalian 116024, China
CCCC Second Harbor Engineering Co., Ltd., Wuhan 430040, China
Funding
National Key R&D Program of China · National Natural Science Foundation of China · Guangxi Key Technologies R&D Program
References (51)
Show source-provided references
1. Displacement model for concrete dam safety monitoring via Gaussian process regression considering extreme air temperature10.1061/(ASCE)ST.1943-541X.0002467 ↗
2. A technical review of hydro-project development in China10.1016/J.ENG.2016.03.008 ↗
3. Technical progress on researches for the safety of high concrete-faced rockfill dams10.1016/J.ENG.2016.03.010 ↗
4. Concrete dam damage detection and localisation based on YOLOv5s-HSC and photogrammetric 3D reconstruction10.1016/j.autcon.2022.104555 ↗
5. Displacement prediction model for high arch dams using long short-term memory based encoder-decoder with dual-stage attention considering measured dam temperature10.1016/j.engstruct.2023.115686 ↗
6. Structural identification of super high arch dams using Gaussian process regression with improved salp swarm algorithm10.1016/j.engstruct.2023.116150 ↗
7. Effect of light source wavelength on surface defect imaging in deep-water concrete dams10.1016/j.ndteint.2024.103198 ↗
8. The ground penetrating radar response recognition of hidden dam defects using multi-output convolutional neural network10.1016/j.jappgeo.2024.105397 ↗
9. Intelligent detection of building cracks based on deep learning10.1016/j.imavis.2020.103987 ↗
10. Shimono, S., Matsubara, O., Toyama, S., and Nishizawa, U. (2015, January 19–22). Development of underwater inspection system for dam inspection. Proceedings of the OCEANS 2015-MTS/IEEE, Washington, DC, USA.10.23919/OCEANS.2015.7401929 ↗
11. Seismic cracking evolution for anti-seepage face slabs in concrete faced rockfill dams based on cohesive zone model in explicit SBFEM-FEM frame10.1016/j.soildyn.2020.106106 ↗
12. High-detail and low-cost underwater inspection of large-scale hydropower dams
13. Autonomous underwater vehicle challenge: Design and construction of a medium-sized, AI-enabled low-cost prototype10.1177/15485129211027236 ↗
14. ROV-Based Autonomous Maneuvering for Ship Hull Inspection with Coverage Monitoring10.1007/s10846-024-02095-2 ↗
15. Kazmi, W., Ridao, P., Romagos, D.R., and Hernandez, E. (2009, January 12–17). Dam wall detection and tracking using a mechanically scanned imaging sonar. Proceedings of the 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan.10.1109/ROBOT.2009.5152691 ↗
16. Method for 3D reconstruction of surface diseases of underwater concrete structures based on ROV
17. Autonomous underwater vehicle to inspect hydroelectric dams
18. Chen, D., Huang, B., and Kang, F. (2023). A review of detection technologies for underwater cracks on concrete dam surfaces. Appl. Sci., 13.10.3390/app13063564 ↗
19. Sakagami, N., Takemura, F., Ono, R., Katagiri, C., Nakanishi, Y., and Yamamoto, Y. (2015, January 28–30). Observation support system of an ROV for underwater archaeology. Proceedings of the 2015 International Conference on Intelligent Informatics and Biomedical Sciences, Okinawa, Japan.10.1109/ICIIBMS.2015.7439498 ↗
20. Cheng, C., Wang, C., Yang, D., Liu, W., and Zhang, F. (2022). Underwater localization and mapping based on multi-beam forward looking sonar. Front. Neurorobotics, 15.10.3389/fnbot.2021.801956 ↗
21. Autonomous and remotely operated vehicle technology for hydrothermal vent discovery, exploration, and sampling10.5670/oceanog.2007.89 ↗
22. Shi, P., Fan, X., and Wang, G. (2015, January 14–15). A novel underwater dam crack detection algorithm based on sonar images. Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering (ICCSAE 2015), Sanya, China.
23. Sugimoto, H., Moriya, Y., and Ogasawara, T. (2017, January 21–24). Underwater survey system of dam embankment by remotely operated vehicle. Proceedings of the 2017 IEEE Underwater Technology (UT), Busan, Republic of Korea.10.1109/UT.2017.7890298 ↗
24. Visual inspection of hydroelectric dams using an autonomous underwater vehicle10.1002/rob.20351 ↗
25. Development of dam inspection robot with negative pressure effect plate10.1002/rob.21911 ↗
26. Key Technology and Practice of Underwater Intelligent Inspection in Multiple Scenarios of Hydropower Station
27. Study of underwater robotic GDROV programme for dam detection
28. Deep learning10.1038/nature14539 ↗
29. Machine learning and deep learning10.1007/s12525-021-00475-2 ↗
30. Shinde, P., and Shah, S. (2018, January 16–18). A review of machine learning and deep learning applications. Proceedings of the 2018 Fourth International Conference on Computing Communication Control And Automation (ICCUBEA), Pune, India.10.1109/ICCUBEA.2018.8697857 ↗
31. Feng, C., Zhang, H., Wang, H., Wang, S., and Li, Y. (2020). Automatic pixel-level crack detection on dam surface using deep convolutional network. Sensors, 20.10.3390/s20072069 ↗
32. Measurement of concrete crack feature with android smartphone APP based on digital image processing techniques10.1016/j.measurement.2019.107093 ↗
33. Pixel-level multicategory detection of visible seismic damage of reinforced concrete components10.1111/mice.12667 ↗
34. Automatic detection of sewer defects based on improved you only look once algorithm10.1016/j.autcon.2021.103912 ↗
35. Concrete crack detection and quantification using deep learning and structured light10.1016/j.conbuildmat.2020.119096 ↗
36. A real-time detection approach for bridge cracks based on YOLOv4-FPM10.1016/j.autcon.2020.103514 ↗
37. Pavement distress detection using convolutional neural networks with images captured via UAV10.1016/j.autcon.2021.103991 ↗
38. Underwater crack pixel-wise identification and quantification for dams via lightweight semantic segmentation and transfer learning10.1016/j.autcon.2022.104600 ↗
39. Torrey, L., and Shavlik, J. (2010). Transfer learning. Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, IGI Global.10.4018/978-1-60566-766-9.ch011 ↗
40. A survey on transfer learning10.1109/TKDE.2009.191 ↗
41. An underwater dam crack image segmentation method based on multi-level adversarial transfer learning10.1016/j.neucom.2022.07.036 ↗
42. Detecting large-scale underwater cracks based on remote operated vehicle and graph convolutional neural network10.1007/s11709-022-0855-8 ↗
43. Micro-concrete crack detection of underwater structures based on convolutional neural network10.1007/s00138-022-01327-5 ↗
44. A method of underwater bridge structure damage detection method based on a lightweight deep convolutional network10.1049/ipr2.12602 ↗
45. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas10.3390/make5040083 ↗
46. Wu, Y., Han, Q., Jin, Q., Li, J., and Zhang, Y. (2023). LCA-YOLOv8-Seg: An Improved Lightweight YOLOv8-Seg for Real-Time Pixel-Level Crack Detection of Dams and Bridges. Appl. Sci., 13.10.3390/app131910583 ↗
47. Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18–24). A convnet for the 2020s. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01167 ↗
48. Bai, H., and Liang, X. (2024). A very lightweight image super-resolution network. Sci. Rep., 14.10.1038/s41598-024-64724-y ↗
49. Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., and Sun, X. (2022). Damo-yolo: A report on real-time object detection design. arXiv.
50. Sun, Z., Li, P., Meng, Q., Sun, Y., and Bi, Y. (2023). An Improved YOLOv5 Method to Detect Tailings Ponds from High-Resolution Remote Sensing Images. Remote Sens., 15.10.3390/rs15071796 ↗
51. Focal and efficient IOU loss for accurate bounding box regression10.1016/j.neucom.2022.07.042 ↗