Quantitative Evaluation of Crack Damage Based on U<sup>2</sup>-Net and Morphology

LI Yunhui; KANG Shuai; HE Dongqing; Ding Yapeng

doi:10.3724/j.gyjzG23110710

Volume 54 Issue 11

Nov. 2024

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2024 > 54(11): 67-77

LI Yunhui, KANG Shuai, HE Dongqing, Ding Yapeng. Quantitative Evaluation of Crack Damage Based on U2-Net and Morphology[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(11): 67-77. doi: 10.3724/j.gyjzG23110710

Citation:

LI Yunhui, KANG Shuai, HE Dongqing, Ding Yapeng. Quantitative Evaluation of Crack Damage Based on U²-Net and Morphology[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(11): 67-77. doi: 10.3724/j.gyjzG23110710

LI Yunhui, KANG Shuai, HE Dongqing, Ding Yapeng. Quantitative Evaluation of Crack Damage Based on U2-Net and Morphology[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(11): 67-77. doi: 10.3724/j.gyjzG23110710

Citation:

PDF( 14366 KB)

Quantitative Evaluation of Crack Damage Based on U²-Net and Morphology

doi: 10.3724/j.gyjzG23110710

School of Civil Engineering, Henan University, Kaifeng 475004, China

Received Date: 2023-11-07
Available Online: 2024-12-05

Abstract

Abstract

Aiming at the problem of uneven classification of apparent crack data and quantification of damage characteristics of concrete structures, a crack damage assessment method based on U²-Net and morphology was proposed. The Dice loss function and the loss weight were fused to construct the loss function, and the loss function was embedded in transfer learning. The U²-Net network was used to train the data set of apparent cracks of concrete members. The skeleton of the predicted crack map was extracted according to the predicted crack binary image, and finally the cracks were divided into linear cracks and mesh cracks. According to different types of cracks, the corresponding characteristic parameters were extracted by morphology, and the error analysis of the corresponding fracture characteristic parameters was carried out to verify the validity of the fracture characteristic parameters. The results showed that: the average relative errors of linear fracture length, maximum width and average width were -1.34%, 1.08% and 2.64%, respectively, and the average relative errors of mesh fracture area and coverage were 0.05% and 0.07%, respectively. It showed that this method had relatively high detection precision and had certain reference value for crack detection of concrete structures.
- U²-Net,
- Dice loss function,
- crack quantification,
- morphology,
- unbalanced data

FullText(HTML)

References(30)

References

[1]	RAFIEI M H, ADELI H. A novel machine learning-based algorithm to detect damage in high-rise building structures [J]. The Structural Design of Tall and Special Buildings, 2017, 26(18), e1400.
[2]	GRAYBEAL B A, PHARES B M, ROLANDER D D, et al. Visual inspection of highway bridges [J]. Journal of Nondestructive Evaluation, 2002, 21(3): 67-83.
[3]	刘宇飞, 樊健生, 聂建国, 等.结构表面裂缝数字图像法识别研究综述与前景展望[J]. 土木工程学报, 2021, 54(6): 79-98.
[4]	HSIEH Y A, TSAI Y J. Machine learning for crack detection: review and model performance comparison [J]. Journal of Computing in Civil Engineering, 2020, 34(5), 04020038.
[5]	LIU Y, YAO J, LU X, et al. Deep Crack: a deep hierarchical feature learning architecture for crack segmentation [J]. Neurocomputing, 2019, 338: 139-153.
[6]	DUNG C V. Autonomous concrete crack detection using deep fully convolutional neural network [J]. Automation in Construction, 2019, 99: 52-58.
[7]	李伟, 申浩, 马志丹, 等. 基于深度卷积网络的路面裂缝分割方法[C]//2019世界交通运输大会论文集(下). 北京:2019: 346-356.
[8]	杨明, 刘露, 郭愫愫. 机器视觉在船舶焊缝图像缺陷分割检测中的应用[J]. 舰船科学技术, 2021, 43(18): 217-219.
[9]	李怡静, 程浩东, 李火坤, 等. 基于改进U²-Net与迁移学习的无人机影像堤防裂缝检测[J]. 水利水电科技进展, 2022, 42(6): 52-59.
[10]	王盛, 吴浩, 彭宁, 等. 改进U²-Net的太阳能电池片缺陷分割方法[J]. 国外电子测量技术, 2023, 42(2): 177-184.
[11]	FAN Z, WU Y, LU J, et al. Automatic pavement crack detection based on structured prediction with the convolutional neural network[EB/OL].[2018-02-01]. https://doi.org/10.48550/arXiv.1803.02208.
[12]	章世祥, 张汉成, 李西芝, 等. 基于机器视觉的路面裂缝病害多目标识别研究[J]. 公路交通科技, 2021, 38(3): 30-39.
[13]	谭云峰, 刘昆, 莫洪柳, 等. 基于优化U-Net的路面裂缝分割及其影响因素研究[J]. 公路交通科技, 2023, 40(12): 17-25.
[14]	YU J, WU C, LI Y, et al. Intelligent identification of coal crack in CT images based on deep learning[J/OL]. Computational Intelligence and Neuroscience, 2022[2023-11-07]. https://doi.org/10.1155/2022/7092436.
[15]	WONG K C L, MORADI M, TANG H, et al. 3D segmentation with exponential logarithmic loss for highly unbalanced object sizes[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2018. Granada: 2018: 612-619.
[16]	彭博, 蒋阳升, 蒲云. 基于数字图像处理的路面裂缝自动分类算法[J]. 中国公路学报, 2014, 27(9): 10-18 , 24.
[17]	LI S, ZHAO X, ZHOU G. Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network [J]. Computer-Aided Civil and Infrastructure Engineering, 2019, 34(7): 616-634.
[18]	丁威, 俞珂, 舒江鹏. 基于深度学习和无人机的混凝土结构裂缝检测方法[J]. 土木工程学报, 2021, 54(增刊1): 1-12.
[19]	YANG X, LI H, YU Y, et al. Automatic pixel-level crack detection and measurement using fully convolutional network [J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(12): 1090-1109.
[20]	QIN X, ZHANG Z, HUANG C, et al. U²-Net: going deeper with nested U-structure for salient object detection [J]. Pattern Recognition, 2020, 106, 107404.
[21]	CHENG H, LI Y, LI H, et al. Embankment crack detection in UAV images based on efficient channel attention U²Net[J].Structures, 2023, 50: 430-443.
[22]	GUO Y, SHI L, ZHANG J. U²-Net: a stacked and nested network with axial attention for detection of building surface cracks[C]//2022 IEEE Smartworld, Ubiquitous Intelligence & Computing, Scalable Computing & Communications, Digital Twin, Privacy Computing, Metaverse, Autonomous & Trusted Vehicles (SmartWorld/UIC/ScalCom/DigitalTwin/PriComp/Meta). Haikou, China: 2022: 1292-1297.
[23]	ZHENG Z, YANG K. Wall crack detection method based on improved YOLOv5 and U2-Net[J]. International Journal of Wireless and Mobile Computing, 2023, 25(4): 362-367.
[24]	陈其浩, 孙林, 张倩. 基于改进U²-Net的透明件划痕检测方法[J]. 科学技术与工程, 2022, 22(2): 620-627.
[25]	孙佳佳, 李承礼, 常德显, 等. 基于生成对抗网络的入侵检测类别不平衡问题数据增强方法[J]. 科学技术与工程, 2022, 22(18): 7965-7971.
[26]	LIU Y, YAO J, LU X, et al. DeepCrack: a deep hierarchical feature learning architecture for crack segmentation [J]. Neurocomputing, 2019, 338: 139-153.
[27]	LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: 2015: 3431-3440.
[28]	CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV). Munich, Germany: 2018: 801-818.
[29]	RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Munich, Germany: 2015:234-241.
[30]	于锦程. 基于深度学习的桥梁表观裂缝量化识别研究[D]. 大连: 大连理工大学, 2022.