Deep Learning-Based Crack Detection in Concrete Bridge Decks and Pavements: A Experimental Review

Chunlei Zhao; Sihan Yan; Ziqin Ye; Yuanyuan Cao; Zhan Zhang; Liwei Wu

doi:10.54691/15c0na71

Deep Learning-Based Crack Detection in Concrete Bridge Decks and Pavements: A Experimental Review

Chunlei Zhao, Sihan Yan, Ziqin Ye, Yuanyuan Cao, Zhan Zhang, Liwei Wu

Frontiers in Science and Engineering, (2025), Vol.5, No.12, pp.107-112

Published: December 24, 2025

DOI: 10.54691/15c0na71

PDF: Download Full Text PDF

Abstract

As transportation infrastructure gradually ages and maintenance costs continue to rise, efficient and precise defect detection of bridges, road surfaces, and concrete structures has become a critical factor in ensuring operational safety. Traditional manual crack identification methods are not only inefficient and subjective but also pose safety risks. The rapid advancement of computer vision and artificial intelligence technologies, particularly deep learning, offers effective solutions to address these challenges. This paper systematically reviews research on the application of deep learning models in typical tasks such as crack image classification, object localization, and pixel-level segmentation. It provides an in-depth analysis of the recognition mechanisms, technical advantages, and applicable scenarios of mainstream models, including convolutional neural networks and generative adversarial networks. Furthermore, it summarizes experimental findings and presents personal insights, aiming to provide reference and facilitate further research and application of deep learning in the intelligent maintenance and management of civil engineering infrastructure.

Keywords: Deep Learning, Attention Mechanism, Convolutional Neural Network (CNN).

APA Citation: Chunlei Zhao, Sihan Yan, Ziqin Ye, Yuanyuan Cao, Zhan Zhang, Liwei Wu (2025). Deep Learning-Based Crack Detection in Concrete Bridge Decks and Pavements: A Experimental Review. Frontiers in Science and Engineering, 5(12), 107-112. https://doi.org/10.54691/15c0na71

References

Pan Y, Zhou S X, Huang X S, et al. A deep learning-based concrete crack identification method incorporating textural features[J]. Concrete, 2024, (02): 45-51, 57.
CHEN Ruiqi. Research on Concrete Crack Identification Method Based on Lightweight Convolutional Neural Network[D]. Sichuan Normal University, 2025. DOI:10.27347/d.cnki.gssdu.2025.001868.
XU Jiaqi. Research on Concrete Crack Identification Method Based on Edge Extraction and VGG16 Deep Convolutional Neural Network[J]. Construction Technology(Chinese and English), 2023, 52(09): 11-15.
Wu X H, Zhou X L, Wang Y Q. Research on concrete crack identification method based on ResNet+ network model[J]. Highway, 2025, 70(10): 381-388.
XU Liang, HE Wei, YEERDA·Yeerdingdala, et al. Research on Methods and Mechanisms of Concrete Crack Detection Using UAV Intelligent Inspection[J]. Water Resources and Hydropower Engineering(Chinese and English), 2024, 55(S1): 249-256. DOI:10.13928/j.cnki.wrahe.2024.S1.039.
ZHU Qiankun, XIE Chenhui, ZHANG Qiong, et al. Ancient Bridge Crack Identification Method Based on Computer Vision and Deep Learning[J/OL]. Journal of Southwest Jiaotong University, 1-12[2025-11-15]. Link.
YANG G J, QI Y H, DU Y F, et al. Bridge crack identification and measurement using improved YOLOv7 and SeaFormer[J]. Journal of Railway Science and Engineering, 2025, 22(01): 429-442. DOI:10.19713/j.cnki.43-1423/u.T20240458.
TANG Yong, YAO Xuechun, WANG Chen, et al. Automatic Bridge Crack Recognition System Based on UAV Image Technology and Support Vector Machine (SVM)[J]. Highway Engineering, 2024, 49(06): 49-56. DOI:10.19782/j.cnki.1674-0610.2024.06.008.
FENG H L, LIU Y F, LIU X G, et al. Research on two-stage identification algorithm for bridge cracks based on convolutional neural network[J/OL]. Engineering Mechanics, 1-13[2025-11-15]. https://link.cnki.net/urlid/11.2595.O3.20250113.1014.002.
ZHOU Shuangxi, YANG Dan, PAN Yuan, et al. Pavement Crack Detection and Recognition Using YOLOv5 with Attention Mechanism[J]. Journal of East China Jiaotong University, 2024, 41(02): 56-63. DOI:10.16749/j.cnki.jecjtu.20240307.002.