New Metrics to Benchmark and Improve BIM Visibility Within a Synthetic Image Generation Process for Computer Vision Progress Tracking

Juan D. Nunez-Morales, Shun Hsiang Hsu, Amir Ibrahim, Mani Golparvar-Fard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Data collection, particularly ground-truth generation, is crucial for developing computer vision models used for construction progress monitoring applications. The performance of such models relies heavily on the quality of the data, which drives the effectiveness of machine learning algorithms. If data is not collected and subsequently managed correctly, the algorithms will fail, and the applicability of these models for construction monitoring applications will be degraded. In the absence of quality data, synthetic image generation using BIM has been widely studied to resolve data insufficiency issues. Because of the domain gap between synthetic and real-world images, most recent works have focused on rendering techniques to enhance the realism of lighting and texture. However, the impact of extrinsic camera parameters, which directly influence how BIM elements are rendered in camera views, is heavily underexplored. This leads to an over-utilization of weakly created synthetic ground-truth images. As a result, these images and their often-random camera position and viewpoints fail to reflect real-world visual perspectives needed for enterprise-grade solutions for monitoring construction progress. To improve the quality of synthetic construction environment datasets, this paper explores the integration of per-element visibility metrics to understand how different positional camera parameters impact the synthetic data collection pipeline and segmentation model performance improvement. This work is validated by comparing real-image segmentation accuracy through experiments using visibility metrics from different camera positions and directions. Finally, a discussion of how positional camera parameters can be selected for producing a more efficient and less biased synthetic dataset is presented.

Original languageEnglish (US)
Title of host publicationProceedings of the Canadian Society for Civil Engineering Annual Conference 2023 - Construction Track
EditorsSerge Desjardins, Gérard J. Poitras, Mazdak Nik-Bakht
PublisherSpringer
Pages209-221
Number of pages13
ISBN (Print)9783031614989
DOIs
StatePublished - 2025
EventCanadian Society of Civil Engineering Annual Conference, CSCE 2023 - Moncton, Canada
Duration: May 24 2023May 27 2023

Publication series

NameLecture Notes in Civil Engineering
Volume498 LNCE
ISSN (Print)2366-2557
ISSN (Electronic)2366-2565

Conference

ConferenceCanadian Society of Civil Engineering Annual Conference, CSCE 2023
Country/TerritoryCanada
CityMoncton
Period5/24/235/27/23

Keywords

  • Automated progress monitoring
  • BIM
  • Computer vision
  • Deep learning
  • Synthetic data

ASJC Scopus subject areas

  • Civil and Structural Engineering

Fingerprint

Dive into the research topics of 'New Metrics to Benchmark and Improve BIM Visibility Within a Synthetic Image Generation Process for Computer Vision Progress Tracking'. Together they form a unique fingerprint.

Cite this