«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

卷:

41卷

期数:

2024年05期

页码:

14-22

栏目:

建筑结构

出版日期:

2024-09-20

文章信息/Info

Title:

Crack localization and tracking in concrete structures based on 3D point cloud reconstruction

文章编号:

1673-2049(2024)05-0014-09

作者:

周姝康¹,丁 威¹,金振奋^2,3,俞 珂⁴,张 鹤¹,舒江鹏^1,2,3

(1. 浙江大学 建筑工程学院,浙江 杭州 310058; 2. 浙江大学 平衡建筑研究中心,浙江 杭州 310058; 3. 浙江大学建筑设计研究院有限公司,浙江 杭州 310058; 4. 西北大学 土木工程系,伊利诺伊 埃文斯顿 IL60208)

Author(s):

ZHOU Shukang¹, DING Wei¹, JIN Zhenfen^2,3, YU Ke⁴, ZHANG He¹, SHU Jiangpeng^1,2,3

(1. College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, Zhejiang, China; 2. Center for Balance Architecture, Zhejiang University, Hangzhou 310058, Zhejiang, China; 3. The Architecture Design & Research Institution of Zhejiang University Co., Ltd, Hangzhou 310058, Zhejiang, China; 4. Civil and Environmental Engineering Department, Northwestern University, Evanston IL60208, Illinois, USA)

关键词:

裂缝定位;  宽度量化;  裂缝扩展跟踪;  三维点云重建;  视点定位;  点云映射

Keywords:

crack localization;  width quantization;  crack propagation tracking;  3D point cloud reconstruction;  viewpoint localization;  point cloud mapping

分类号:

TU37

DOI:

10.19815/j.jace.2022.10119

文献标志码:

A

摘要:

为实现混凝土结构裂缝的自动化定位、宽度量化及扩展追踪,提出一种基于三维点云重建的混凝土结构裂缝定位及扩展追踪方法。首先通过无人机搭载高分辨率云台相机获取目标建筑物的图像集,再通过优化数据集与三维重建流程得到准确的建筑结构点云模型,并还原相机空间参数; 然后提出视点定位算法,基于还原的相机空间参数求得拍摄裂缝的相机世界坐标,将裂缝图片与相机世界坐标绑定,基于图片索引裂缝的三维坐标,实现裂缝在点云模型中的自动定位; 最后提出适用于混凝土结构的点云映射与配准算法,对裂缝宽度的扩展进行量化追踪。通过试验对服役期的大型混凝土建筑结构进行了可行性和精度验证。结果表明:所提出方法的三维模型重建的尺度平均误差小于3%,且可自动化定位结构裂缝的三维坐标,裂缝平均定位时间为38.09 μs; 通过进一步将整体模型与更新的裂缝点云集配准,可实现裂缝扩展信息(裂缝宽度)的准确追踪,试验相对误差小于8%。

Abstract:

In order to realize automatic crack localization, width quantification, and extension tracking in concrete structure, a methodology for crack localization and tracking in concrete structures based on three-dimensional(3D)point cloud reconstruction was proposed. Firstly, the image set of the target building was obtained by an unmanned aerial vehicle(UAV)equipped with a high-resolution gimbal camera. Image acquisition and 3D reconstruction process were optimized to obtain an accurate point cloud model of the building structure and restore the camera space parameters. Secondly, the viewpoint localization algorithm was proposed to obtain the camera world coordinates of the cracks based on the restored camera space parameters. After binding the crack images to the world coordinates of cameras, the 3D coordinates of the crack were indexed based on the image to realize the automatic localization of the crack in the point cloud model. Finally, point cloud mapping and the registration algorithm for concrete structures was proposed to quantitatively track the propagation of crack width. The feasibility and accuracy of the large concrete building structure in service period were verified by experiments. The results show that the average scale error of 3D model reconstruction by the method is less than 3%, and the 3D coordinates of structure cracks can be automatically located. The average localization time of cracks is 38.09 μs, and by further registering the whole model with the updated crack point cloud set, the accurate tracking of crack propagation information(crack width)can be realized, and the test relative error is less than 8%.

参考文献/References:

[1] 丁 威,马亥波,舒江鹏,等.基于残差网络的混凝土结构病害分类识别研究[J].建筑科学与工程学报,2022,39(4):127-136.
DING Wei,MA Haibo,SHU Jiangpeng,et al.Research on classification and recognition of concrete structure diseases based on residual network[J].Journal of Architecture and Civil Engineering,2022,39(4):127-136.
[2]杨 铄,许清风,王卓琳.基于卷积神经网络的结构损伤识别研究进展[J].建筑科学与工程学报,2022,39(4):38-57.
YANG Shuo,XU Qingfeng,WANG Zhuolin.Research progress on structural damage detection based on convolutional neural networks[J].Journal of Architecture and Civil Engineering,2022,39(4):38-57.
[3]邵旭东,罗 军,曹君辉,等.钢-UHPC轻型组合桥面结构试验及裂缝宽度计算研究[J].土木工程学报,2019,52(3):61-75.
SHAO Xudong,LUO Jun,CAO Junhui,et al.Experimental study and crack width calculation of steel-UHPC lightweight composite deck structure[J].China Civil Engineering Journal,2019,52(3):61-75.
[4]DANCYGIER A N,ARINSKI Y S.Effect of cracking localization on the structural ductility of normal strength and high strength reinforced concrete beams with steel fibers[J].International Journal of Protective Structures,2019,10(4):457-469.
[5]WANG X,ZHAO Z H,LI N,et al.Pavement crack analysis by referring to historical crack data based on multi-scale localization[J].PLOS ONE,2020,15(8):e0235171.
[6]LI C,XU P,NIU L,et al.Tunnel crack detection using coarse-to-fine region localization and edge detection[J].WIREs Data Mining and Knowledge Discovery,2019,9(5):e1308.
[7]ZHANG B,ZHOU Z,LI X.A Crack monitoring method for concrete structures[J].Intelligent Automation & Soft Computing,2010,16(5):763-770.
[8]QI C,WEI X Y,JUN L,et al.A research on fatigue crack growth monitoring based on multi-sensor and data fusion[J].Structural Health Monitoring,2021,20(3):848-860.
[9]舒江鹏,李 俊,马亥波,等.基于特征金字塔网络的超大尺寸图像裂缝识别检测方法[J].土木与环境工程学报(中英文),2022,44(3):29-36.
SHU Jiangpeng,LI Jun,MA Haibo,et al.Crack detection method based on feature pyramid network for super large-scale images[J].Journal of Civil and Environmental Engineering,2022,44(3):29-36.
[10]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1):1-12.
DING Wei,YU Ke,SHU Jiangpeng.Method for detecting cracks in concrete structures based on deep learning and UAV[J].China Civil Engineering Journal,2021,54(S1):1-12.
[11]LIU Y,NIE X,FAN J,et al.Image-based crack assessment of bridge piers using unmanned aerial vehicles and three-dimensional scene reconstruction[J].Computer-aided Civil and Infrastructure Engineering,2020,35(5):511-529.
[12]KIM D,KWAK Y,SOHN H.Accelerated cable-stayed bridge construction using terrestrial laser scanning[J].Automation in Construction,2020,117:103269.
[13]VETRIVEL A,GERKE M,KERLE N,et al.Identification of damage in buildings based on gaps in 3D point clouds from very high resolution oblique airborne images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2015,105:61-78.
[14]MOMTAZ DARGAHI M,KHALOO A,LATTANZI D.Color-space analytics for damage detection in 3D point clouds[J].Structure and Infrastructure Engineering,2022,18(6):775-788.
[15]LIU X,DYKE S J,YEUM C M,et al.Automated indoor image localization to support a post-event building assessment[J].Sensors,2020,20(6):1610.
[16]吕忠达.杭州湾跨海大桥关键技术研究与实施[J].土木工程学报,2006(6):78-82,87.
LU Zhongda.Key technologies for Hangzhou bay bridge[J].China Civil Engineering Journal,2006(6):78-82,87.
[17]KONG S,FAN J,LIU Y,et al.Automated crack assessment and quantitative growth monitoring[J].Computer-aided Civil and Infrastructure Engineering,2021,36(5): 656-674.
[18]邱志强,于起峰.从建筑物序列图像恢复三维结构[J].武汉大学学报(工学版),2003(3):13-15,25.
QIU Zhiqiang,YU Qifeng.3D building structure from image sequence[J].Engineering Journal of Wuhan University,2003(3):13-15,25.
[19]PANTOJA-ROSERO B G,ACHANTA R,KOZINSKI M,et al.Generating LOD3 building models from structure-from-motion and semantic segmentation[J].Automation in Construction,2022,141:104430.
[20]QIU W,JIAN L,CHENG Y,et al.Three-dimensional reconstruction of tunnel face based on multiple images[J].Advances in Civil Engineering,2021,2021:1-11.
[21]ELKHRACHY I.3D Structure from 2D dimensional images using structure from motion algorithms[J].Sustainability,2022,14(9):5399.
[22]LI S,XU C,XIE M.A robust o(n)solution to the perspective-n-point problem[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(7):1444-1450.
[23]HAMDAN A H,TARABEN J,HELMRICH M,et al.A semantic modeling approach for the automated detection and interpretation of structural damage[J].Automation in Construction,2021,128:103739.

相似文献/References:

备注/Memo

备注/Memo:

收稿日期:2022-10-28
基金项目:国家自然科学基金青年科学基金项目(52108179); 浙江省自然科学基金探索项目(Q22E088936); 浙江省交通运输厅科技计划项目(202217)
通信作者:舒江鹏(1987-),男,工学博士,研究员,博士生导师,E-mail:jpeshu@zju.edu.cn。

常用功能

更新日期/Last Update: 2024-09-30