基于三维重建的结构表面裂缝检测方法

张昊宇; 丁勇; 李登华

doi:10.13204/j.gyjzG22102611

基于三维重建的结构表面裂缝检测方法

doi: 10.13204/j.gyjzG22102611

张昊宇¹,
丁勇^1, ,,
李登华^2,3

1. 南京理工大学理学院, 南京 210094;
2. 南京水利科学研究院, 南京 210029;
3. 水利部水库大坝安全重点实验室, 南京 210029

基金项目:

国家自然科学基金项目(51979174)

中央级公益性科研院所基本科研业务费专项资金资助项目(Y321004)。

国家重点研发计划(2022YFC3005502)

国家自然科学基金联合基金项目(U2040221)

详细信息

作者简介:
张昊宇,硕士研究生,主要从事结构健康监测研究,zhanghaoyu1956@126.com。

通讯作者:
丁勇,博士,副教授,硕士生导师,主要从事结构健康监测研究,njustding@163.com。

计量
- 文章访问数: 123
- HTML全文浏览量: 14
- PDF下载量: 4
- 被引次数: 0
出版历程
- 收稿日期: 2022-10-26
- 网络出版日期: 2024-06-22

A Structural Surface Crack Detection Method Based on 3D Reconstruction

ZHANG Haoyu¹,
DING Yong^{1
, ,},
LI Denghua^2,3

1. Nanjing University of Science and Technology, Nanjing 210094, China;
2. Nanjing Research Institute of Water Resources, Nanjing 210029, China;
3. Key Laboratory of Reservoir Dam Safety, Ministry of Water Resources, Nanjing 210029, China

摘要

摘要: 针对传统基于数字图像处理的裂缝监测方法缺乏对裂缝区域参数集成化表达,提出一种基于三维重建的结构表面裂缝检测方法。该方法在提高裂缝边缘识别精度的同时,实现了裂缝的区域集成及参数计算。使用二维裂缝映射到三维模型的方法完成裂缝的定位。根据建筑物的立面高度和结构特点,规划摄影路径、采集影像数据、构建针对建筑裂缝的影像数据集;结合SfM重建技术建立裂缝所在外立面区域三维模型,根据相机光心到裂缝所在拟合平面的距离,实现无测距设备条件下物距信息的获取;利用级联神经网络完成结构表面裂缝的识别与分割;利用实景三维模型获取像素解析度完成裂缝参数的计算。试验结果表明,所提方法可准确识别建筑外立面裂缝,同时计算裂缝宽度和长度,最终完成裂缝集成与定位。裂缝宽度相对误差小于1.5%,具有良好的实用价值。
- 混凝土裂缝检测 /
- 深度学习 /
- 三维实景模型 /
- 像素解析度
Abstract: In view of the lack of integrated expression of crack region parameters in traditional digital image processing-based crack monitoring methods, the paper proposed a structural surface crack detection method based on three-dimensional reconstruction. This method not only improves the accuracy of crack edge recognition but also realizes the integration of crack regions and parameter calculation. The location of cracks can be determined by mapping two-dimensional cracks onto three-dimensional models. The main work includes: planning the photographic path, collecting image data, and constructing an image dataset targeting building cracks according to the facade height and structural characteristics of the building; establishing a three-dimensional model of the exterior facade area with cracks using Structure from Motion SfM reconstruction technology, and obtaining object distance information without the need for ranging equipment based on the distance from the camera center to the crack fitting plane; identifying and segmenting structural surface cracks using cascaded neural networks; calculating crack parameters using the pixel resolution obtained from the real-world 3D model. The experimental results demonstrated that the proposed method could accurately identify cracks in building facades while simultaneously calculating crack widths and lengths, ultimately achieving crack integration and localization. The relative error of crack width is less than 1.5%, indicating good practical value.
- concrete crack detection /
- deep learning /
- 3D realistic model /
- pixel resolution

HTML全文

参考文献(17)

[1]	MWA B, WWA B, DZA B, et al. The pixel crack reconstruction method: from fracture image to crack geological model for fracture evolution simulation-ScienceDirect[J/OL]. Construction and Building Materials, 2021[2020-12-02].https://doi.org/10.1016/j.conbuildmat.2020.121733.
[2]	LIAO K W, LEE Y T. Detection of rust defects on steel bridge coatings via digital image recognition[J].Automation in Construction, 2016,71:294-306.
[3]	张振海, 尹晓珍, 王阳萍, 等. 基于特征分析的图像式地铁隧道裂缝检测方法研究[J]. 铁道科学与工程学报, 2019,16(11):2791-2800.
[4]	贺福强, 平安, 罗红, 等. 局部特征聚类联合区域增长的桥梁裂缝检测[J]. 科学技术与工程, 2019,19(34):272-277.
[5]	TULBURE A A, ADRIAN-ALEXANDRU T, HENRIETTA E D. A review on modern defect detection models using DCNNs-Deep convolutional neural networks[J]. Journal of Advanced Research, 2022,35:33-48.
[6]	YLA B, TBAB C, BO X D, et al. A deep residual neural network framework with transfer learning for concrete dams patch-level crack classification and weakly-supervised localization[J/OL]. Measurement, 2022[2021-12-23].https://doi.org/10.1016/j.measurement.2021.110641.
[7]	陈健昌, 张志华. 融于图像多特征的路面裂缝智能化识别[J]. 科学技术与工程, 2021,21(24):10491-10497.
[8]	徐国整, 廖晨聪, 陈锦剑, 等. 基于HU-ResNet的混凝土表观裂缝信息提取[J]. 计算机工程, 2020,46(11):279-285.
[9]	MA Z, LIU S. A review of 3D reconstruction techniques in civil engineering and their applications[J].Advanced Engineering Informatics, 2018,37:163-174.
[10]	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.
[11]	曹霆, 王卫星, 杨楠, 等. 基于三维激光扫描技术的路面断板深度检测[J]. 红外与激光工程, 2017,46(2):88-93.
[12]	张辉霖, 李登华, 丁勇. 面向混凝土裂缝检测的级联神经网络算法研究[J]. 水力发电学报, 2022,41(8):134-143.
[13]	刘学增, 叶康. 隧道衬砌裂缝的远距离图像测量技术[J]. 同济大学学报(自然科学版), 2012,40(6):829-836.
[14]	吴玉龙, 岳大森, 丁勇, 等. 基于图像处理的膨胀圆裂缝检测算法[J]. 无损检测, 2020,42(3):9-13.
[15]	Zhang T Y, Suen C Y. A fast parallel algorithm for thinning digital patterns[J]. Communications of the ACM, 1984,27(3):236-239.
[16]	刘宇飞. 基于模型修正与图像处理的多尺度结构损伤识别[D]. 北京:清华大学, 2015.
[17]	LIU Y, CHO S, SPENCER B F, et al. Concrete crack assessment using digital image processing and 3D scene reconstruction[J/OL].Journal of Computing in Civil Engineering, 2016[2014-12-02].https://doi.org/10.1061/(ASCE)CP.1943-5487.0000446.