«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06期

页码:

31-40

栏目:

建筑结构

出版日期:

2024-11-30

文章信息/Info

Title:

Image visual detection method for rebar engineering quality in concrete structure based on deep learning

文章编号:

1673-2049(2024)06-0031-10

作者:

杜晓庆¹,葛潇峰¹,朱炯亦¹,汪德江¹,蒋海里²,刘攀攀²

(1. 上海大学 力学与工程科学学院,上海 200444; 2. 上海公路桥梁(集团)有限公司,上海 200082)

Author(s):

DU Xiaoqing¹, GE Xiaofeng¹, ZHU Jiongyi¹, WANG Dejiang¹, JIANG Haili², LIU Panpan²

(1. School of Mechanics and Engineering Science, Shanghai University, Shanghai 200444, China; 2. Shanghai Highway and Bridge Group Co., Ltd., Shanghai 200082, China)

关键词:

钢筋工程质量;  深度学习;  目标检测算法;  钢筋交叉点;  像素坐标

Keywords:

rebar engineering quality;  deep learning;  object detection algorithm;  rebar intersection;  pixel coordinate

分类号:

TU317

DOI:

10.19815/j.jace.2023.02092

文献标志码:

A

摘要:

针对目前钢筋工程质量检测中人工抽检方法检测效率低,覆盖面不全的问题,提出一种可实现钢筋间距与直径智能检测的改进YOLOX目标检测算法。该方法基于精确的钢筋交叉点识别,实现钢筋间距与直径检测,在YOLOX目标检测算法中加入坐标注意力机制模块,采用完全交并比损失函数替换原有算法中的边界框回归损失函数,显著提升目标检测算法识别钢筋交叉点及其中心坐标的精准度; 依据钢筋交叉点预测框的像素坐标信息与RGBD相机采集的深度信息,实现钢筋间距检测; 采用整体嵌套边缘检测网络(HED)边缘检测算法消除图片中钢筋肋边缘对统计钢筋直径所含像素个数的干扰,实现钢筋直径的检测。结果表明:采用改进后的算法检测得到的钢筋间距最大误差为4.04 mm,平均误差小于2.8 mm,满足施工规范要求; 当采用改进后的算法检测8、10、16、20、25 mm钢筋直径时,检测值在标准值d₀±1 mm范围内的平均准确率为97.22%。

Abstract:

Aiming at the problems of low detection efficiency and incomplete coverage caused by the current manual sampling method for quality inspection of rebar engineering, an improved YOLOX object detection algorithm was proposed to achieve intelligent detection of rebar spacing and diameter. The method realized rebar spacing and diameter detection based on accurate rebar intersection identification. The coordinate attention mechanism module was added to YOLOX object detection algorithm, and the original loss function for bounding box regression was replaced with the complete intersection over union loss function, which significantly improved the accuracy of the object detection algorithm in detecting both the rebar intersection and its central coordinates. According to the pixel coordinate information from the rebar intersection prediction box, along with depth information collected by the RGBD camera, the rebar spacing detection was realized. The Holistically-nested Edge Detection(HED)edge detection algorithm was used to eliminate the interference of rebar rib edges in the image on the number of pixels included in the statistical rebar diameter, to realize the detection of rebar diameter. The results show that the maximum error of rebar spacing detected by the improved algorithm is 4.04 mm, and the average error is less than 2.8 mm, which meets the requirements of construction specifications. When the improved algorithm is used to detect 8, 10, 16, 20, 25 mm rebar diameters, the average accuracy of the detection value in the range of standard value d₀±1 mm is 97.22%.

参考文献/References:

[1] 王 芳.钢筋工程设计及施工缺陷分析[J].科学技术与工程,2011,11(4):877-880.
WANG Fang.Design and construction defects analysis of ordinary steel bar in reinforced concrete structure[J].Science Technology and Engineering,2011,11(4):877-880.
[2]刘金龙,陆伟东,袁小军.混凝土中不同直径钢筋的雷达图像研究[J].建筑科学,2020,36(7):137-141.
LIU Jinlong,LU Weidong,YUAN Xiaojun.Research on radar images of rebars with different diameters in concrete[J].Building Science,2020,36(7):137-141.
[3]叶爱文,谢慧才.混凝土中钢筋直径雷达检测的神经网络方法[J].建筑科学与工程学报,2008,25(4):105-110.
YE Aiwen,XIE Huicai.Neural network method of diameter detection of rebar in concrete by using GPR[J].Journal of Architecture and Civil Engineering,2008,25(4):105-110.
[4]杨 宇,凌同华,廖艳程.混凝土构件深浅埋钢筋模拟检测试验与偏移分析[J].土木建筑与环境工程,2018,40(6):139-145.
YANG Yu,LING Tonghua,LIAO Yancheng.Simulation test and migration analysis for detection signal of deep and shallow reinforcement in concrete member[J].Journal of Civil,Architectural & Environmental Engineering,2018,40(6):139-145.
[5]刘世龙,马智亮.基于点云的钢筋数量和间距自动检查算法[J].建筑科学与工程学报,2022,39(4):90-99.
LIU Shilong,MA Zhiliang.Automatic inspection algorithm of quantity and spacing of reinforcement based on point cloud[J].Journal of Architecture and Civil Engineering,2022,39(4):90-99.
[6]KIM M K,THEDJA J P P,CHI H L,et al.Automated rebar diameter classification using point cloud data based machine learning[J].Automation in Construction,2021,122:103476.
[7]LI F X,KIM M K,LEE D E.Geometrical model based scan planning approach for the classification of rebar diameters[J].Automation in Construction,2021,130:103848.
[8]HAN K,GWAK J Y,GOLPARVAR-FARD M,et al.Vision-based field inspection of concrete reinforcing bars[C]//DAWOOD N, KASSEM M.Proceedings of the 13th International Conference on Construction Applications of Virtual Reality.London: Teesside University,2013:1-10.
[9]闫天冉,马晓静,饶颖露,等.基于改进Mask R-CNN的建筑钢筋尺寸检测算法[J].计算机工程,2021,47(9):274-281.
YAN Tianran,MA Xiaojing,RAO Yinglu,et al.Rebar size detection algorithom for intelligent construction supervision based on improved Mask R-CNN[J].Computer Engineering,2021,47(9):274-281.
[10]李姚舜,刘黎志.嵌入注意力机制的轻量级钢筋检测网络[J].计算机应用,2022,42(9):2900-2908.
LI Yaoshun,LIU Lizhi.Lightweight network for rebar detection with attention mechanism[J].Journal of Computer Applications,2022,42(9):2900-2908.
[11]XIE S N,TU Z W.Holistically-nested edge detection[J].International Journal of Computer Vision,2017,125(1):3-18.
[12]邵延华,张 铎,楚红雨,等.基于深度学习的YOLO目标检测综述[J].电子与信息学报,2022,44(10):3697-3708.
SHAO Yanhua,ZHANG Duo,CHU Hongyu,et al.A review of YOLO object detection based on deep learning[J].Journal of Electronics & Information Technology,2022,44(10):3697-3708.
[13]YU J,JIANG Y,WANG Z,et al.Unitbox:an advanced object detection network[C]//ALAN H,CEES S,MARCEL W,et al.Proceedings of the 24th ACM International Conference on Multimedia.New York:Association for Computing Machinery,2016:516-520.
[14]HOU Q B,ZHOU D Q,FENG J S.Coordinate attention for efficient mobile network design[C]//IEEE.2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Nashville:IEEE,2021:13708-13717.
[15]PANBOONYUEN T,THONGBAI S,WONGWEERANIMIT W,et al.Object detection of road assets using transformer-based YOLOX with feature pyramid decoder on Thai highway panorama[J].Information,2021,13(1):1-12.
[16]ZHAN J L,HU Y W,CAI W W,et al.PDAM-STPNNet:a small target detection approach for wildland fire smoke through remote sensing images[J].Symmetry,2021,13(12):2260.
[17]LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//IEEE.2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu:IEEE,2017:936-944.
[18]混凝土结构工程施工质量验收规范:GB 50204—2015[S].北京:中国建筑工业出版社,2015.
Code for quality acceptance of concrete structure construction:GB 50204—2015[S].Beijing:China Architecture & Building Press,2015.

相似文献/References:

[1]李书进,赵 源,孔 凡,等.卷积神经网络在结构损伤诊断中的应用[J].建筑科学与工程学报,2020,37(06):29.
　LI Shu-jin,ZHAO Yuan,KONG Fan,et al.Application of Convolutional Neural Network in Structural Damage Identification[J].Journal of Architecture and Civil Engineering,2020,37(06):29.
[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(04):38.[doi:10.19815/j.jace.2022.02043]
　YANG Shuo,XU Qing-feng,WANG Zhuo-lin.Research Progress on Structural Damage Detection Based on Convolutional Neural Networks[J].Journal of Architecture and Civil Engineering,2022,39(06):38.[doi:10.19815/j.jace.2022.02043]
[3]卢昱杰,刘 博,刘金杉,等.面向施工机械的深度学习图像数据集合成方法[J].建筑科学与工程学报,2022,39(04):100.[doi:10.19815/j.jace.2021.07146]
　LU Yu-jie,LIU Bo,LIU Jin-shan,et al.Image Dataset Synthetic Method for Construction Machinery Based on Deep Learning[J].Journal of Architecture and Civil Engineering,2022,39(06):100.[doi:10.19815/j.jace.2021.07146]

备注/Memo

备注/Memo:

收稿日期:2023-11-09
基金项目:国家自然科学基金项目(51978392); 国家自然科学基金青年科学基金项目(52208317); 上海市科技攻关基金项目(20dz1202100); 上海市促进产业高质量发展专项项目(2023-GZL-RGZN-01031)
作者简介:杜晓庆(1973-),男,工学博士,教授,博士生导师,E-mail:dxq@shu.edu.cn。
通信作者:朱炯亦(1989-),男,工学博士,讲师,E-mail:shuzhujy@shu.edu.cn。
Author resumes: DU Xiaoqing(1973-),male,PhD,professor,E-mail:dxq@shu.edu.cn; ZHU Jiongyi(1989-),male,PhD,assistant professor,E-mail:shuzhujy@shu.edu.cn.

常用功能

更新日期/Last Update: 2024-12-10