Tracking Volumetric Units in Modular Factories for Automated Progress Monitoring Using Computer Vision

Roshan Panahi, Joseph Louis, Ankur Podder, Colby Swanson

Research output: Contribution to conferencePaper

10 Scopus Citations


The construction industry is increasingly adopting off-site and prefabricated methods due to advantages offered in safety, quality, and lead time. Applying industrialized methods for plant management in offsite construction factories requires the collection of large volumes of production process data, which is a tedious task when performed manually. Recent attempts to automate this process have relied on sensor-based data collection methods which are susceptible to noise, expensive, and difficult to validate. Computer vision methods, however, enable process data collection from videos without the limitations of the other sensor-based methods. This technology has not been applied for offsite construction except in very few instances and therefore, this study proposes a novel method to reliably collect the production process data using computer vision method in near real-time from widely used surveillance cameras in offsite construction. The proposed method allows the user to annotate the workstations of interest on the video as ground truths and process these areas throughout the entire video to track the units entering and leaving stations, while continuously updating a near real-time schedule of the production line. This framework was validated by implementing on the surveillance videos of the production process of modular home manufacturing in a factory. The results consistently provided 100% accuracy, after denoising, for all the videos processed including 60 h of work for a station. The developed method enables real-time tracking of station performance, which can enable continuous improvement methods for factory management and resource allocation.
Original languageAmerican English
Number of pages8
StatePublished - 2022
EventConstruction Research Congress 2022 - Arlington, Virginia
Duration: 9 Mar 202212 Mar 2022


ConferenceConstruction Research Congress 2022
CityArlington, Virginia

NREL Publication Number

  • NREL/CP-5500-79018


  • computer vision
  • industrialized construction innovation
  • modular construction
  • productivity


Dive into the research topics of 'Tracking Volumetric Units in Modular Factories for Automated Progress Monitoring Using Computer Vision'. Together they form a unique fingerprint.

Cite this