基于计算机视觉的往复荷载作用下钢筋混凝土柱裂缝监测

宋成浩; 陈书成; 胡晓斌; 袁焕鑫

doi:10.13204/j.gyjzG22070112

基于计算机视觉的往复荷载作用下钢筋混凝土柱裂缝监测

doi: 10.13204/j.gyjzG22070112

武汉大学土木建筑工程学院, 武汉 430072

基金项目:

国家自然科学基金项目（51578429）。

详细信息

作者简介:
宋成浩,男,1999年出生,硕士研究生,songchenghao@whu.edu.cn。

通讯作者:
胡晓斌,男,1979年出生,教授,博士生导师,newhxb@126.com。

计量
- 文章访问数: 42
- HTML全文浏览量: 8
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-01
- 网络出版日期: 2023-03-22

Crack Monitoring of RC Columns Under Cyclic Loading Based on Computer Vision

School of Civil Engineering, Wuhan University, Wuhan 430072, China

摘要

摘要: 通过对图像拼接得到大范围裂缝图像，采用阈值分割算法进行裂缝识别，从而建立起基于计算机视觉的混凝土构件表面大范围裂缝识别流程。在此基础上，对往复荷载作用下的钢筋混凝土柱进行裂缝监测，研究加载过程中混凝土柱表面裂缝开展情况。结果表明：采用图像拼接，可以利用消费级手机分区获取裂缝图像，进而识别混凝土构件表面大范围的裂缝；所建立的裂缝识别流程能较好地识别混凝土柱上大范围表面裂缝，裂缝宽度、长度和倾角识别精度较高；随着位移幅值的增加，混凝土柱表面裂缝长度、宽度和面积增加，倾角减小，损伤随之增加。
- 计算机视觉 /
- 裂缝识别 /
- 图像拼接 /
- 往复荷载 /
- 裂缝监测
Abstract: Based on computer vision, the procedure of recognizing wide-range cracks on the surface of concrete members was presented by obtaining the wide-range crack images through image stitching, and identifying cracks by the threshold segmentation. Adopting the procedure, crack monitoring was conducted on a reinforced concrete (RC) column under cyclic loading to study crack development on the surface during loading and unloading processes. The results showed that wide-range concrete surfaces with cracks could be photographed in a sub-regional way with consumer-grade mobile phones. By further stitching the photos together, the cracks were finely recognized. The proposed procedure could be well used to recognize wide-range cracks on the surface of RC columns with relatively higher identification accuracy regarding crack width, length and inclined angles. In addition, with the increase of displacement amplifude, the width, length and areas of cracks on the surface of the RC column increased, the inclined angles decreased, and then the damage increased.
- computer vision /
- wide-range crack recognition /
- image stitching /
- cyclic loading /
- crack monitoring

HTML全文

参考文献(16)

[1]	AMMOUCHE A, BREYSSE D, HORNAIN H, et al. A new image analysis technique for the quantitative assessment of micro cracks in cement-based materials[J]. Cement and Concrete Research, 2000, 30(1):25-35.
[2]	YAMAGUCHI T, NAKAMURA S, SAEGUSA R, et al. Image-based crack detection for real concrete surfaces[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2008, 3(1):128-135.
[3]	刘鹏. 基于图像处理的混凝土预制构件裂缝检测系统研究[D].西安:西安建筑科技大学,2017.
[4]	沈俊凯.基于计算机视觉的混凝土裂缝检测算法研究[D].哈尔滨:中国地震局力学工程研究所,2019.
[5]	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(9):1277-1286.
[6]	SHAN B, ZHENG S, OU J. A stereovision-based crack width detection approach for concrete surface assessment[J].KSCE Journal of Civil Engineering, 2016, 20(2):803-812.
[7]	韩晓健,赵志成.基于计算机视觉技术的结构表面裂缝检测方法研究[J].建筑结构学报,2018(增刊1):418-427.
[8]	BROWN M, LOWE D G. Automatic Panoramic Image Stitching using Invariant Features[J]. International Journal of Computer Vision, 2007, 74(1):59-73.
[9]	HARRIS C, STEPHENS M. A combined corner and edge detector[C]//Proceedings of the 4th alvey vision conference, 1988:189-192.
[10]	FISCHLER M A, BOLLES R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.
[11]	章毓晋. 计算机视觉教程[M]. 北京:人民邮电出版社, 2017.
[12]	YANOWITZ S D, BRUCKSTEIN A M. A new method for image segmentation[J]. Computer Vision Graphics and Image Processing, 1989, 46(1):82-95.
[13]	雷斯达,曹鸿猷,康俊涛.基于深度学习的复杂场景下混凝土表面裂缝识别研究[J].公路交通科技,2020(12):80-88.
[14]	HARALICK R M, SHAPIRO L G. Computer and robot vision[M]. Reading:Addison-Wesley, 1992.
[15]	贾云得. 机器视觉[M]. 北京:科学出版社, 2003.
[16]	The MathWorks, Inc.Image processing toolbox[M/OL]. https://www.mathworks.com/help/images. 2209000020801010陈振明.fbd