«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:

39卷

期数:

2022年04期

页码:

90-99

栏目:

出版日期:

2022-07-12

文章信息/Info

Title:

Automatic Inspection Algorithm of Quantity and Spacing of Reinforcement Based on Point Cloud

文章编号:

1673-2049(2022)04-0090-10

作者:

刘世龙,马智亮

(清华大学 土木工程系,北京 100084)

Author(s):

LIU Shi-long, MA Zhi-liang

(Department of Civil Engineering, Tsinghua University, Beijing 100084, China)

关键词:

点云;  钢筋骨架;  质量检查;  配准;  算法

Keywords:

point cloud;  reinforcement skeleton;  quality inspection;  registration;  algorithm

分类号:

TU973.2

DOI:

10.19815/j.jace.2021.07021

文献标志码:

A

摘要:

为改进钢筋骨架质量自动检查方法,提出了基于点云的钢筋骨架中钢筋数量和钢筋间距的自动检查算法。该算法在获取钢筋骨架实际点云和设计点云的基础上,首先对这两片点云分别进行降采样,以得到空间密集程度相同的钢筋骨架实际点云和设计点云; 其次,对降采样后的钢筋骨架实际点云和设计点云使用基于主成分分析(PCA)的方法进行粗配准。由于粗配准后的钢筋骨架实际点云和设计点云的配准精度较低,无法直接用于钢筋数量和钢筋间距的检查,对粗配准后的钢筋骨架实际点云和设计点云进行精配准。最后,基于精配准得到的钢筋骨架实际点云和设计点云,依次对钢筋骨架中的钢筋数量和钢筋间距进行检查。结果表明:精配准后的钢筋骨架实际点云和设计点云的配准精度较高,可以用于钢筋数量和钢筋间距的检查; 该算法对钢筋数量检查的准确率为100%,对钢筋间距检查的准确率为80%; 应用该算法可以有效提高复杂钢筋骨架中钢筋数量和钢筋间距检查的效率,降低人工成本。

Abstract:

In order to improve the automatic inspection method of reinforcement skeleton quality, an automatic inspection algorithm of quantity and spacing of reinforcement in reinforcement skeleton based on point cloud was proposed. On the basis of obtaining the actual point cloud and the design point cloud of reinforcement skeleton, the algorithm firstly downsampled the two point clouds respectively to obtain the actual point cloud and the design point cloud of reinforcement skeleton with the same spatial density. Secondly, the actual point cloud and design point cloud of the reinforcement skeleton after downsampling were roughly registered by using the method based on principal component analysis(PCA). Due to the low registration accuracy of the actual point cloud and design point cloud of the reinforcement skeleton after coarse registration, it could not be directly used for the inspection of the quantity and spacing of reinforcement, the actual point cloud and design point cloud of the reinforcement skeleton after coarse registration were accurately registered. Finally, based on the actual point cloud and design point cloud of the reinforcement skeleton obtained by fine registration, the quantity and spacing of reinforcement in the reinforcement skeleton were checked in turn. The results show that the registration accuracy of actual point cloud and design point cloud of reinforcement skeleton after fine registration is high, which can be used to check the quantity and spacing of reinforcement. The accuracy of the algorithm is 100% for the number of reinforcement inspection and 80% for the spacing of reinforcement inspection. The application of this algorithm can effectively improve the efficiency of checking the number and spacing of reinforcement in complex reinforcement skeleton and reduce the labor cost.

参考文献/References:

[1] MA Z,LIU S.A Review of 3D Reconstruction Techniques in Civil Engineering and Their Applications[J].Advanced Engineering Informatics,2018,37:163-174.
[2]YANG M D,CHAO C F,HUANG K S,et al.Image-based 3D Scene Reconstruction and Exploration in Augmented Reality[J].Automation in Construction,2013,33:48-60.
[3]SUNG C,KIM P Y.3D Terrain Reconstruction of Construction Sites Using a Stereo Camera[J].Automation in Construction,2016,64:65-77.
[4]PATIL A K,HOLI P,LEE S K,et al.An Adaptive Approach for the Reconstruction and Modeling of As-built 3D Pipelines from Point Clouds[J].Automation in Construction,2017,75:65-78.
[5]WIKIPEDIA.Building Information Modeling[EB/OL].[2022-03-06].https://en.wikipedia.org/wiki/Building_information_modeling.
[6]刘世龙,马智亮.基于BIM的钢筋骨架语义设计点云自动生成算法[J].图学学报,2021,42(5):816-822.
LIU Shi-long,MA Zhi-liang.BIM-based Algorithm for Automatic Generation of Semantic As-designed Point Cloud of Reinforcement Skeleton[J].Journal of Graphics,2021,42(5):816-822.
[7]HSUA H W,HSIEHA S H.Applying Augmented Reality Technique to Support On-site Rebar Inspection[C]//ISARC.Proceedings of the International Symposium on Automation and Robotics in Construction.Banff:ISARC,2019:1312-1318.
[8]WANG Q,CHENG J C P,SOHN H.Automated Estimation of Reinforced Precast Concrete Rebar Positions Using Colored Laser Scan Data[J].Computer-aided Civil and Infrastructure Engineering,2017,32(9):787-802.
[9]KIM M K,THEDJA J P P,WANG Q.Automated Dimensional Quality Assessment for Formwork and Rebar of Reinforced Concrete Components Using 3D Point Cloud Data[J].Automation in Construction,2020,112:103077.
[10]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.
[11]RADU B R,STEVE C.Downsampling a Pointcloud Using a Voxelgrid Filter[EB/OL].[2021-03-25].https://pointclouds.org/documentation/tutorials/voxel_grid.html.
[12]KIM C,SON H,KIM C.Automated Construction Progress Measurement Using a 4D Building Information Model and 3D Data[J].Automation in Construction,2013,31:75-82.
[13]Anon.Principal Component Analysis[EB/OL].[2021-03-25].https://en.wikipedia.org/wiki/Principal_component_analysis.
[14]JAADI Z.A Step-by-step Explanation of Principle Co-mponent Analysis[EB/OL].[2021-03-25].https://builtin.com/data-science/step-step-explanation-principal-component-analysis.
[15]Anon.Random Sample Consensus[EB/OL].[2021-04-28].https://en.wikipedia.org/wiki/Random_sample_consensus.
[16]装配式混凝土结构表示方法及示例(剪力墙结构):15G107-1[S].北京:中国计划出版社,2015.
Representation Method and Example of Fabricated Concrete Structure(Shear Wall Structure):15G107-1[S].Beijing:China Planning Press,2015.

相似文献/References:

备注/Memo

备注/Memo:

收稿日期:2021-07-04
基金项目:国家自然科学基金项目(51678345)
作者简介:刘世龙(1991-),男,江苏邳州人,工学博士研究生,E-mail:erickrt@163.com。
通信作者:马智亮(1963-),男,陕西府谷人,教授,博士研究生导师,工学博士,E-mail:mazl@tsinghua.edu.cn。

常用功能

更新日期/Last Update: 2022-07-10