Vision-based scene understanding : preliminary study on concrete placement progress monitoring

Tools

Lim, Seungmo and Kim, Junghoon and Jeong, Insoo and Ryu, Yelin and Chi, Seokho; Moreno-Rangel, Alejandro and Kumar, Bimal, eds. (2025) Vision-based scene understanding : preliminary study on concrete placement progress monitoring. In: EG-ICE 2025. University of Strathclyde Publishing, GBR. ISBN 9781914241826 (https://doi.org/10.17868/strath.00093255)

[thumbnail of Lim-etal-EG-ICE-2025-Vision-based-scene-understanding-preliminary-study-on-concrete]
Preview
 Text. Filename: Lim-etal-EG-ICE-2025-Vision-based-scene-understanding-preliminary-study-on-concrete.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

Conventional construction progress monitoring relies on manual processes like on-site inspections and paper-based reporting, making it labor-intensive, time-consuming, and prone to human error. Recent advancements in vision technologies have enabled the automation of progress monitoring. This study proposes a 2D vision-based construction progress monitoring framework for monitoring concrete placement. The framework integrates instance inpainting to address occlusions caused by dynamic construction objects, and performs single image-based 3D reconstruction using monocular depth estimation for precise progress evaluation. Experimental results demonstrated strong alignment with ground truth, while also indicating the framework’s potential to distinguish between different work states over time. The proposed framework contributes to the widespread implementation of automated progress monitoring across diverse construction sites.

  • Item type:Book Section
    ID code:93255
    Dates:
    Date
    Event
    1 July 2025
    Published
    9 June 2025
    Accepted
    Subjects:Fine Arts > Architecture
    Department:Faculty of Engineering > Architecture
    Depositing user: Pure Administrator
    Date deposited:27 Jun 2025 10:37
    Last modified:01 Jul 2025 11:27
    URI:https://strathprints.strath.ac.uk/id/eprint/93255
CORE (COnnecting REpositories)