基于深度学习的裂缝识别与量化分析研究

范存君; 金松燕; 金楠; 施钟淇; 伍永靖邦; 郝新田

doi:10.3724/j.gyjzG24061802

基于深度学习的裂缝识别与量化分析研究

doi: 10.3724/j.gyjzG24061802

范存君^1,2,3,
金松燕^1,2,3, ,,
金楠^1,2,3,
施钟淇^1,2,3,
伍永靖邦^1,2,3,
郝新田^1,2,3

1. 深圳市城市公共安全技术研究院有限公司, 深圳市城市灾害数字孪生重点实验室, 广东深圳 518023;
2. 城市安全发展科技研究院(深圳), 广东深圳 518023;
3. 城市安全风险监测预警应急管理部重点实验室, 广东深圳 518023

基金项目:

青年人才托举工程(2023QNRC001)。

深圳市科技计划资助(ZDSYS20210929115800001,KJZD20231023093057005)

国家重点研发计划资助(2022YFC3800304)

详细信息

作者简介:
范存君,硕士,主要从事无人机智能巡检、计算机视觉方向的研究,fancj@szsti.org。

通讯作者:
金松燕,硕士,主要从事机载激光雷达巡检、地理信息系统方向的研究,jinsy@szsti.org。

计量
- 文章访问数: 189
- HTML全文浏览量: 13
- PDF下载量: 9
- 被引次数: 0
出版历程
- 收稿日期: 2024-06-18
- 网络出版日期: 2024-09-19

Crack Recognition and Quantitative Analysis Based on Deep Learning

FAN Cunjun^1,2,3,
JIN Songyan^{1,2,3
, ,},
JIN Nan^1,2,3,
SHI Zhongqi^1,2,3,
WU Yongjingbang^1,2,3,
HAO Xintian^1,2,3

1. Shenzhen Urban Public Safety and Technology Institute, Shenzhen Key Laboratory of Urban Disasters Digital Twin, Shenzhen 518023, China;
2. Safe Urban Development Institute of Science and Technology (Shenzhen), Shenzhen 518023, China;
3. Key Laboratory for Urban Safety Risk Monitoring and Early Warning of Emergency Management Department, Shenzhen 518023, China

摘要

摘要: 裂缝是混凝土结构中常见的表观损伤之一,对结构性能的评估具有重要的意义。利用计算机视觉技术对混凝土结构表面进行裂缝识别与量化已得到广泛研究,然而,基于深度学习的裂缝识别技术依赖于大规模的裂缝数据集进行训练。为此,提出基于风格迁移网络的数据增广方法,利用少量裂缝数据和各种背景图像数据,构建大规模的、复杂背景的裂缝数据集,并通过训练YoloV8网络模型实现裂缝的识别与分割,并根据裂缝特性,对识别结果中的孤立、微小区域进行滤除。在此基础上,基于已知参考标志物进行裂缝宽度量化分析,试验结果表明裂缝宽度计算误差基本控制在20%以内。
- 深度学习 /
- 数据扩充 /
- 裂缝识别 /
- 裂缝宽度
Abstract: Cracks are a common form of surface damage in concrete structures and have significant implications for assessing structural performance. The use of computer vision techniques for crack recognition and quantification on the surface of concrete structures has been widely studied. However, deep learning-based crack recognition techniques rely on large-scale crack datasets for training. To address this issue, the paper proposed a data augmentation method based on style transfer networks. A large-scale, complex-background crack dataset was constructed by using a small amount of crack data and various background image data. The YoloV8 network model was trained to achieve crack recognition and segmentation. Based on the crack characteristics, isolated and tiny areas in the recognition results were filtered. Based on this, crack width quantification analysis was performed based on known reference markers, and the experimental results showed that the calculation error of crack widths was basically controlled within 20%.
- deep learning /
- data augmentation /
- crack recognition /
- crack width

HTML全文

参考文献(19)

[1]	LIU Y, YEOH J K W. Robust pixel-wise concrete crack segmentation and properties retrieval using image patches[J]. Automation in Construction, 2021, 123, 103535.
[2]	TSAI Y C, KAUL V, MERSEREAU R M. Critical assessment of pavement distress segmentation methods[J]. Journal of Transportation Engineering, 2010, 136(1):11-19.
[3]	KOCH C, GEORGIEVA K, KASIREDDY V, et al. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure[J]. Advanced Engineering Informatics, 2015, 29(2): 196-210.
[4]	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.
[5]	ZHOU S, SONG W. Concrete roadway crack segmentation using encoder-decoder networks with range images[J]. Automation in Construction, 2020, 120, 103403.
[6]	WANG W, SU C. Semi-supervised semantic segmentation network for surface crack detection[J]. Automation in Construction, 2021, 128, 103786.
[7]	SPENCER JR B F, HOSKERE V, NARAZAKI Y. Advances in computer vision-based civil infrastructure inspection and monitoring[J]. Advances in Civil Engineering, 2019, 5(2): 199-222.
[8]	WANG H, LI Y, DANG L M, et al. Pixel-level tunnel crack segmentation using a weakly supervised annotation approach[J]. Computers in Industry, 2021, 133, 103545.
[9]	杨国俊,齐亚辉,石秀名.基于数字图像技术的桥梁裂缝检测综述[J].吉林大学学报(工学版),2024,54(2):313-332.
[10]	周颖,刘彤.基于计算机视觉的混凝土裂缝识别[J].同济大学学报(自然科学版),2019,47(9):1277-1285.
[11]	谢文高,张怡孝,刘爱荣,等.基于水下机器人与数字图像技术的混凝土结构表面裂缝检测方法[J].工程力学,2022,39(增刊1):64-70.
[12]	余加勇,李锋,薛现凯,等.基于无人机及Mask R-CNN的桥梁结构裂缝智能识别[J].中国公路学报,2021,34(12):80-90.
[13]	刘宇飞,樊健生,孔思宇,等.多视角几何三维重建法识别工程结构缺损与变形[J].工程力学,2020,37(9):103-111.
[14]	KOONCE B.MobileNetV3[M]//Convolutional neural networks with swift for Tensorflow. Berkeley, CA: Apress, 2021.
[15]	WEN L, GAO C, ZOU C. CAP-VSTNet: content affinity preserved versatile style transfer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 18300-18309.
[16]	TERVEN J, CORDOVA-ESPARZA D. A comprehensive review of YOLO: from YOLOv1 to YOLOv8 and beyond[J/OL]. arXiv preprint arXiv:2304.00501, 2023.https://arxiv.org/pdf/2304.00501v1
[17]	OCHER G, CHAURASIA A, QIU J. ULTRALYTICS YOLO (VERSION 8.0.0)[EB/OL]. [2024-06-18].https://github.com/ultralytics/ultralytics.
[18]	ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.
[19]	周道德,高豆豆,董登峰,等.基于深度学习和PnP模型的激光跟踪仪自动姿态测量[J].光学精密工程,2022,30(9):1047-1057.