基于深度学习的混凝土裂缝识别与几何参数评估

IF 4 2区 工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Advances in Engineering Software Pub Date : 2024-10-30 DOI:10.1016/j.advengsoft.2024.103800
Wang Shaowei, Xu Jiangbo, Wu Xiong, Zhang Jiajun, Zhang Zixuan, Chen Xinyu
{"title":"基于深度学习的混凝土裂缝识别与几何参数评估","authors":"Wang Shaowei,&nbsp;Xu Jiangbo,&nbsp;Wu Xiong,&nbsp;Zhang Jiajun,&nbsp;Zhang Zixuan,&nbsp;Chen Xinyu","doi":"10.1016/j.advengsoft.2024.103800","DOIUrl":null,"url":null,"abstract":"<div><div>Concrete cracks will greatly affect the normal use function of buildings. Traditional crack detection and image processing methods have problems such as large amounts of calculation and low detection accuracy. In this paper, the DeepLabV3+ network model is improved by introducing CBAM and ECANet attention mechanisms. The backbone stem module is changed to three 3 × 3 convolutions with larger receptive fields, and three low-level feature maps are extracted as input maps for the decoder to enhance semantic information, and finally form the C-E-DeepLabV3+ model. The method proposed in this paper is validated by integrating multiple typical crack image libraries such as Crack500. The results show that the MIoU value can reach 77.84 %, which is 4 %, 5.53 %, 6.52 %, 4.49 % and 3.44 % higher than the original model DeepLabV3+, advanced segmentation model YOLOv8x, classical segmentation models UNet, MobileNet and PSPNet, respectively. And in terms of model parameter amount, it is 39 % lower than the original DeepLabV3+ model, and compared to other traditional models, it is only slightly higher than the lightweight model MobileNet. On this basis, the orthogonal skeleton line method is used to calculate the length and width of segmented cracks. Compared with the actual measured values, the accuracy of the method in this paper can reach more than 93 %, which has good engineering applicability.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"199 ","pages":"Article 103800"},"PeriodicalIF":4.0000,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Concrete crack recognition and geometric parameter evaluation based on deep learning\",\"authors\":\"Wang Shaowei,&nbsp;Xu Jiangbo,&nbsp;Wu Xiong,&nbsp;Zhang Jiajun,&nbsp;Zhang Zixuan,&nbsp;Chen Xinyu\",\"doi\":\"10.1016/j.advengsoft.2024.103800\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Concrete cracks will greatly affect the normal use function of buildings. Traditional crack detection and image processing methods have problems such as large amounts of calculation and low detection accuracy. In this paper, the DeepLabV3+ network model is improved by introducing CBAM and ECANet attention mechanisms. The backbone stem module is changed to three 3 × 3 convolutions with larger receptive fields, and three low-level feature maps are extracted as input maps for the decoder to enhance semantic information, and finally form the C-E-DeepLabV3+ model. The method proposed in this paper is validated by integrating multiple typical crack image libraries such as Crack500. The results show that the MIoU value can reach 77.84 %, which is 4 %, 5.53 %, 6.52 %, 4.49 % and 3.44 % higher than the original model DeepLabV3+, advanced segmentation model YOLOv8x, classical segmentation models UNet, MobileNet and PSPNet, respectively. And in terms of model parameter amount, it is 39 % lower than the original DeepLabV3+ model, and compared to other traditional models, it is only slightly higher than the lightweight model MobileNet. On this basis, the orthogonal skeleton line method is used to calculate the length and width of segmented cracks. Compared with the actual measured values, the accuracy of the method in this paper can reach more than 93 %, which has good engineering applicability.</div></div>\",\"PeriodicalId\":50866,\"journal\":{\"name\":\"Advances in Engineering Software\",\"volume\":\"199 \",\"pages\":\"Article 103800\"},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2024-10-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in Engineering Software\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0965997824002072\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Engineering Software","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0965997824002072","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

混凝土裂缝会严重影响建筑物的正常使用功能。传统的裂缝检测和图像处理方法存在计算量大、检测精度低等问题。本文通过引入 CBAM 和 ECANet 注意机制,改进了 DeepLabV3+ 网络模型。将骨干干模块改为三个具有更大感受野的 3 × 3 卷积,并提取三个底层特征图作为解码器的输入图,以增强语义信息,最终形成 C-E-DeepLabV3+ 模型。本文提出的方法通过整合 Crack500 等多个典型裂纹图像库进行了验证。结果表明,MIoU 值可以达到 77.84 %,分别比原始模型 DeepLabV3+、高级分割模型 YOLOv8x、经典分割模型 UNet、MobileNet 和 PSPNet 高出 4 %、5.53 %、6.52 %、4.49 % 和 3.44 %。而在模型参数量方面,它比原始模型 DeepLabV3+ 低 39%,与其他传统模型相比,仅略高于轻量级模型 MobileNet。在此基础上,采用正交骨架线法计算分割裂缝的长度和宽度。与实际测量值相比,本文方法的精度可达 93 % 以上,具有良好的工程适用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Concrete crack recognition and geometric parameter evaluation based on deep learning
Concrete cracks will greatly affect the normal use function of buildings. Traditional crack detection and image processing methods have problems such as large amounts of calculation and low detection accuracy. In this paper, the DeepLabV3+ network model is improved by introducing CBAM and ECANet attention mechanisms. The backbone stem module is changed to three 3 × 3 convolutions with larger receptive fields, and three low-level feature maps are extracted as input maps for the decoder to enhance semantic information, and finally form the C-E-DeepLabV3+ model. The method proposed in this paper is validated by integrating multiple typical crack image libraries such as Crack500. The results show that the MIoU value can reach 77.84 %, which is 4 %, 5.53 %, 6.52 %, 4.49 % and 3.44 % higher than the original model DeepLabV3+, advanced segmentation model YOLOv8x, classical segmentation models UNet, MobileNet and PSPNet, respectively. And in terms of model parameter amount, it is 39 % lower than the original DeepLabV3+ model, and compared to other traditional models, it is only slightly higher than the lightweight model MobileNet. On this basis, the orthogonal skeleton line method is used to calculate the length and width of segmented cracks. Compared with the actual measured values, the accuracy of the method in this paper can reach more than 93 %, which has good engineering applicability.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Advances in Engineering Software
Advances in Engineering Software 工程技术-计算机:跨学科应用
CiteScore
7.70
自引率
4.20%
发文量
169
审稿时长
37 days
期刊介绍: The objective of this journal is to communicate recent and projected advances in computer-based engineering techniques. The fields covered include mechanical, aerospace, civil and environmental engineering, with an emphasis on research and development leading to practical problem-solving. The scope of the journal includes: • Innovative computational strategies and numerical algorithms for large-scale engineering problems • Analysis and simulation techniques and systems • Model and mesh generation • Control of the accuracy, stability and efficiency of computational process • Exploitation of new computing environments (eg distributed hetergeneous and collaborative computing) • Advanced visualization techniques, virtual environments and prototyping • Applications of AI, knowledge-based systems, computational intelligence, including fuzzy logic, neural networks and evolutionary computations • Application of object-oriented technology to engineering problems • Intelligent human computer interfaces • Design automation, multidisciplinary design and optimization • CAD, CAE and integrated process and product development systems • Quality and reliability.
期刊最新文献
Refined finite element analysis of helical wire ropes under multi-axial dynamic loading An engineering-oriented Shallow-water Hydro-Sediment-Morphodynamic model using the GPU-acceleration and the hybrid LTS/GMaTS method Dimensionality reduction of solution reconstruction methods for a four-point stencil Stress-constrained topology optimization of geometrically nonlinear continuum structures by using parallel computing strategy .A multi-objective search-based approach for position and orientation deviations in assemblies with multiple non-ideal surfaces
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1