|Table of Contents|

Reverse modeling method for concrete beam based on classifications of density of point cloud(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2022年6期
Page:
23-32
Research Field:
桥梁工程·交通基础设施智能化运维技术专栏
Publishing date:

Info

Title:
Reverse modeling method for concrete beam based on classifications of density of point cloud
Author(s):
WU Wen-qing1;  LIU Hong-yi1;  WANG Xin-ya1;  ZHOU Xiao-yi1;  TANG Zhi-qiang2;  LI Yan-jun2
(1. School of Transportation, Southeast University, Nanjing 211189, Jiangsu, China; 2. Wuxi Communications Construction Engineering Group Co.,Ltd, Wuxi 214000, Jiangsu, China)
Keywords:
bridge engineering;  concrete precast beam;  virtual assembly;  LiDAR;  reverse modeling;  Voronoi diagram;  characteristic point
PACS:
U466.2
DOI:
10.19721/j.cnki.1671-8879.2022.06.003
Abstract:
In order to underlie the virtual assembly of precast concrete bridges, needed the reverse modeling based on LiDAR for the prefabricated components of on-site bridges, so as to convert the actual components made on site into virtual models for subsequent analysis. The quality of 3D laser scanning point cloud obtained on site, concentrated on the definition of characteristic points and corresponding extraction algorithms of them, and an automatic reverse modeling method according to the geometric characteristics of precast concrete beam components was proposed, which could adapt to different quality of point cloud. In this method, the size and pose of the point cloud were firstly identified by transforming the prior data from the design drawings. Then the normal vectors of the points were accurately computed by the iterative weighted PCA, and each point in the measured point cloud was classified according to the normal vectors. The Voronoi diagrams of the point clouds in the adjacent areas of the modeling characteristic points were generated to analyze the distribution and density of these point clouds. Finally, extraction methods of the characteristic points for different density of the point clouds in different adjacent areas were designed, the fitting coordinates were computed, and the reverse modeling of the prefabricated components were completed. The reverse modeling method was used to automatically compute the fitting values for the coordinates of the modeling characteristic points, from which some key dimensions of the components were extracted to verify the accuracy of this method. The results show that this method can automatically analyze the quality of different structural panels, and correspondingly choose the appropriate method to compute the fitting values. The maximum absolute error of all the items is 6 mm while the maximum relative error is 0.4%. It has relatively high modeling accuracy for concrete beam components under actual engineering conditions and certain engineering value.5 tabs, 14 figs, 23 refs.

References:

[1] 赵佳琦,周 勇,何 欣,等.基于深度学习的点云分割研究进展分析[J/OL].电子与信息学报,2022:1-15[2022-07-11].http://kns.cnki.net/kcms/detail/11.4494.tn.20211213.1522.006.html
ZHAO Jia-qi,ZHOU Yong,HE Xin,et al.Research progress analysis of point cloud segmentation based on deep learning[J/OL].Journal of Electronics & Information Technology,2022:1-15[2022-07-11].http://kns.cnki.net/kcms/detail/11.4494.tn.20211213.
1522.006.html
[2]WANG W,XU Y,REN Y C,et al.Parsing of urban facades from 3D point clouds based on a novel multi-view domain[J].Photogrammetric Engineering & Remote Sensing,2021,87(4):283-293.
[3]郭 浩.点云库PCL从入门到精通[M].北京:机械工业出版社,2019.
GUO Hao.Point cloud library(PCL)from beginner to master[M].Beijing:China Machine Press,2019.
[4]SANCHEZ J,DENIS F,COEURJOLLY D,et al.Robust normal vector estimation in 3D point clouds through iterative principal component analysis[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,163:18-35.
[5]MENG X,HE W T,LIU J Y.An investigation of the high efficiency estimation approach of the large-scale scattered point cloud normal vector[J].Applied Sciences,Basel,2018,8(3): 454.
[6]程效军,贾东峰,程小龙.海量点云数据处理理论与技术[M].上海:同济大学出版社,2014.
CHENG Xiao-jun,JIA Dong-feng,CHENG Xiao-long.Theory and technology of massive point cloud data processing[M].Shanghai:Tongji University Press,2014.
[7]MELLADO N,AIGER D,MITRA N J.Super 4PCS fast global pointcloud registration via smart indexing[J].Computer Graphics Forum,2014,33(5):205-215.
[8]周绪红,刘界鹏,程国忠,等.基于点云数据的大型复杂钢拱桥智能虚拟预拼装方法[J].中国公路学报,2021,34(11):1-9.
ZHOU Xu-hong,LIU Jie-peng,CHENG Guo-zhong,et al.Intelligent virtual trial assembly of large and complex steel arch bridges based on point cloud data[J].China Journal of Highway and Transport,2021,34(11):1-9.
[9]KHALOO A,LATTANZI D.Robust normal estimation and region growing segmentation of infrastructure 3D point cloud models[J].Advanced Engineering Informatics,2017,34:1-16.
[10]GUO Y L,WANG H Y,HU Q Y,et al.Deep learning for 3D point clouds:A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,43(12):4338-4364.
[11]PENG Y J,CHANG M,WANG Q,et al.Sparse-to-dense multi-encoder shape completion of unstructured point cloud[J].IEEE Access,2020,8:30969-30978.
[12]CHEN X,RAVIKUMAR N,XIA Y,et al.Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds[J].Medical Image Analysis,2021,74:102228.
[13]ZHAO W J,JIANG Y,LIU Y Y,et al.Automated recognition and measurement based on three-dimensional point clouds to connect precast concrete components[J].Automation in Construction,2022,133:104000.
[14]LIU F Y,LI S P,ZHANG L Q,et al.3DCNN-DQN-RNN:A deep reinforcement learning framework for semantic parsing of large-scale 3D point clouds[C]//IEEE.Proceedings of 2017 IEEE International Conference on Computer Vision.New York:IEEE:5679-5688.
[15]CHARLES R Q,HAO S,MO K C,et al.PointNet:Deep learning on point sets for 3D classification and segmentation[C]//IEEE.Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE:77-85.
[16]NAHANGI M,YEUNG J,HAAS C T,et al.Automated assembly discrepancy feedback using 3D imaging and forward kinematics[J].Automation in Construction,2015,56:36-46.
[17]ZHANG G W,PAN Y,ZHANG L M.Deep learning for detecting building facade elements from images considering prior knowledge[J].Automation in Construction,2022,133:104016.
[18]LI W M,SONG P F.A modified ICP algorithm based on dynamic adjustment factor for registration of point cloud and CAD model[J].Pattern Recognition Letters,2015,65:88-94.
[19]COMBES B,PRIMA S.An efficient EM-ICP algorithm for non-linear registration of large 3D point sets[J].Computer Vision and Image Understanding,2020,191:102854.
[20]ZYDEK A,WERMIN’SKI M,TRYBULA M E.Description of grain boundary structure and topology in nanocrystalline aluminum using Voronoi analysis and order parameter[J].Computational Materials Science,2021,197:110660.
[21]周绪红.建筑智能建造技术初探及其应用[M].北京:中国建筑工业出版社,2021.
ZHOU Xu-hong.Preliminary study and application of intelligent building technology[M].Beijing:China Architecture & Building Press,2021.
[22]张文胜,郝孜奇,王丙占,等.基于点云的隧道改建工程BIM建模方法与实践[J].长安大学学报(自然科学版),2021,41(1):59-68.
ZHANG Wen-sheng,HAO Zi-qi,WANG Bing-zhan,et al.BIM modeling method and practice of tunnel reconstructionproject based on point cloud[J].Journal of Chang’an University(Natural Science Edition),2021,41(1):59-68.
[23]周志华.机器学习[M].北京:清华大学出版社,2016.
ZHOU Zhi-hua.Machine learning[M].Beijing:Tsinghua University Press,2016.

Memo

Memo:
-
Last Update: 2022-12-20