Vision-based inspection of prefabricated components using camera poses: Addressing inherent limitations of image-based 3D reconstruction

Doyun Lee, Guang Yu Nie, Kevin Han

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

Modular construction can lead to additional cost overruns and delays when a defect is found on the construction site and is not easily repairable. Researchers have developed various methods that use image-based 3D reconstruction for quality assessment, but they have inherent limitations, such as inconsistency and dealing with surfaces with reflectivity and limited visual features. Therefore, this paper presents a vision-based quality assessment method using cameras for prefabricated components by addressing these limitations. Specifically, this paper proposes a novel quality inspection method with sub-millimeter accuracy using cameras focused on leveraging camera poses (as opposed to 3D point clouds that are often not consistent in quality) from the image-based 3D reconstruction. The 3D point estimation by computing triangulation was used for achieving accurate measurement. The proposed method is validated using six different variances and two case studies – an aluminum pipe with a reflective surface and a fabricated concrete column. The results demonstrate the accuracy and effectiveness of the proposed method.

Original languageEnglish
Article number105710
JournalJournal of Building Engineering
Volume64
DOIs
StatePublished - Apr 1 2023
Externally publishedYes

Scopus Subject Areas

  • Civil and Structural Engineering
  • Architecture
  • Building and Construction
  • Safety, Risk, Reliability and Quality
  • Mechanics of Materials

Keywords

  • Modular construction
  • Prefabricated components
  • Quality assessment
  • Vision-based inspection

Fingerprint

Dive into the research topics of 'Vision-based inspection of prefabricated components using camera poses: Addressing inherent limitations of image-based 3D reconstruction'. Together they form a unique fingerprint.

Cite this