A method for detecting construction deviations in large and complex building structures utilizing synthetic point clouds for segmentation

Point cloud‐based construction quality assessment and quality control (QA/QC) are playing an increasingly important role in large‐scale complex building projects. However, this approach faces several challenges, such as the laborious and time‐intensive process of manual point cloud segmentation, the high cost of point cloud labeling, and the lack of sufficient training data for deep learning‐based automatic segmentation methods. To address these issues, this paper proposed a method for detecting construction deviations in large‐scale complex building structures by utilizing synthetic point clouds for segmentation. The method automatically generated labeled synthetic point clouds with Gaussian noise using BIM and a virtual engine, significantly augmenting the limited amount of real point cloud data to train the semantic segmentation model, enabling the achievement of 94.2% overall accuracy (OA) and 81.1% mean intersection over union (M_IoU). Furthermore, a point cloud instance segmentation method according to density‐based spatial clustering of applications with noise (DBSCAN) and voxel‐vs‐BIM was proposed to independently compare each instance object of different building components with its corresponding BIM model, assessing the construction accuracy of each component based on root mean square error metric and the level of accuracy specification. For components with an LOA3 accuracy level, further deviation analysis was conducted. Taking the structural construction deviation detection of beams, columns, and concrete thick shells in the core area of the Shanghai Grand Opera House as a case, the proposed method significantly improved the efficiency of QA/QC.

• Publication year

  2025

• Venue

  Computer-Aided Civil and Infrastructure Engineering

• Publication date

  2025-11-28

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1111/mice.70171
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep learning applications for point clouds in the construction industry

  2024cited by this paper
• Automated production of synthetic point clouds of truss bridges for semantic and instance segmentation using deep learning models

  2024cited by this paper
• A lightweight Transformer‐based neural network for large‐scale masonry arch bridge point cloud segmentation

  2024cited by this paper
• Automated flatness assessment for large quantities of full‐scale precast beams using laser scanning

  2024cited by this paper
• Enhancing point cloud semantic segmentation in the data‐scarce domain of industrial plants through synthetic data

  2024cited by this paper
• Research on steel structure point cloud skeleton extraction and construction accuracy evaluation based on BIM model assistance

  2024cited by this paper
• Point Cloud-Based Smart Building Acceptance System for Surface Quality Evaluation

  2023cited by this paper
• End-to-end point cloud-based segmentation of building members for automating dimensional quality control

  2023cited by this paper
• ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution

  2023cited by this paper
• Visual programming simulator for producing realistic labeled point clouds from digital infrastructure models

  2023cited by this paper
• 3D reconstruction of large-scale scaffolds with synthetic data generation and an upsampling adversarial network

  2023cited by this paper
• Quality assurance for building components through point cloud segmentation leveraging synthetic data

  2023cited by this paper
• A deep learning-based indoor acceptance system for assessment on flatness and verticality quality of concrete surfaces

  2022cited by this paper
• Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

  2022cited by this paper
• SIMULATING LIDAR TO CREATE TRAINING DATA FOR MACHINE LEARNING ON 3D POINT CLOUDS

  2022cited by this paper
• Three-dimensional laser scanning for large-scale as-built surveying of 2022 Beijing Winter Olympic Speed Skating Stadium: A case study

  2022cited by this paper
• BIM-driven data augmentation method for semantic segmentation in superpoint-based deep learning network

  2022cited by this paper
• Automated semantic segmentation of bridge point cloud based on local descriptor and machine learning

  2022cited by this paper
• Automated extraction of structural beam lines and connections from point clouds of steel buildings

  2021cited by this paper
• High-precision detection method for large and complex steel structures based on global registration algorithm and automatic point cloud generation

  2021cited by this paper
• HYBRID ACQUISITION OF HIGH QUALITY TRAINING DATA FOR SEMANTIC SEGMENTATION OF 3D POINT CLOUDS USING CROWD-BASED ACTIVE LEARNING

  2020cited by this paper
• Drift Invariant Metric Quality Control of Construction Sites Using BIM and Point Cloud Data

  2020cited by this paper
• Learning from Synthetic Point Cloud Data for Historical Buildings Semantic Segmentation

  2020cited by this paper
• RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

  2019influential reference
• KPConv: Flexible and Deformable Convolution for Point Clouds

  2019cited by this paper
• Detection of Structural Components in Point Clouds of Existing RC Bridges

  2018cited by this paper
• Dimensional accuracy and structural performance assessment of spatial structure components using 3D laser scanning

  2018cited by this paper
• RBFOpt: an open-source library for black-box optimization with costly function evaluations

  2018cited by this paper
• PointCNN: Convolution On X-Transformed Points

  2018cited by this paper
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

  2017cited by this paper
• Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs

  2017influential reference
• Automatic Morphologic Analysis of Quasi‐Periodic Masonry Walls from LiDAR

  2016cited by this paper
• Automated dimensional quality assurance of full-scale precast concrete elements using laser scanning and BIM

  2016cited by this paper
• Automated construction quality assessment: A review

  2015cited by this paper
• Sample Elimination for Generating Poisson Disk Sample Sets

  2015cited by this paper
• Localization and Quantification of Concrete Spalling Defects Using Terrestrial Laser Scanning

  2015cited by this paper
• Application and Research of 3D Laser Scanning Technology in Steel Structure Installation and Deformation Monitoring

  2014cited by this paper
• Opossum

  2013cited by this paper
• Industrialized Construction of Large-Scale High Speed Railway Projects: The Modena Bridges in Italy

  2011cited by this paper
• A New Approach for Health Monitoring of Structures: Terrestrial Laser Scanning

  2007cited by this paper
• Efficient variants of the ICP algorithm

  2001cited by this paper
• The causes and costs of defects in construction. A study of seven building projects

  1999cited by this paper
• Probabilistic Principal Component Analysis

  1999influential reference
• A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise

  1996influential reference
• A Method for Registration of 3-D Shapes

  1992cited by this paper

• No citing papers are available for this paper.