Con-API’s Progress Monitoring Research
Focuses on tracking construction progress, schedule adherence, and deviations.
Our work in Progress Monitoring explores how to systematically measure, compare, and analyze construction progress using modern tools such as digital twins, BIM, computer vision, and AI-powered schedule alignment models. The core aim is to replace manual reporting with automated real-time, data-driven insights that enhance decision-making and project transparency. This division of our lab works towards enhancing construction efficiency through optimized and streamlined information delivery.
Research themes:
- Vision-based schedule tracking
- BIM and reality model integration
- Automatic progress deviation detection
- Digital twin–based status monitoring
- Daily and task-level progress reports
Featured Representative Works
1. Pal, A., Lin, J. J.*, Hsieh, S. H., & Golparvar-Fard, M. (2024). Activity-level construction progress monitoring through semantic segmentation of 3D-informed orthographic images. Automation in Construction, 157, 105157. (SCI) ❐
A combination of Fig. 25 & Fig. 28. Visualization of segmentation on synthetic images and progress tracking via color-coded as-planned BIM alongside semantic segmentation of as-built point cloud.
This paper introduces the novel ALPMS (Activity-Level Progress Monitoring System) framework which tracks the percent completion of construction tasks by activity. This method can provide granular and quantitative information unlike traditional binary methods. Using new solutions such as projective transformation or NeRF (Neural Radiance Fields), orthographic projections are semantically segmented to detect the current stage of each building element.
Site photographs are generated into as-built 3D point clouds and is aligned with the project’s 4D BIM. The progress metrics is then passed back into the BIM for 3D visualization and schedule updates. Validated on two building projects, ALPMS achieved high accuracy, reporting activity-level completion with less than 6% mean absolute error.
2. Pal, A., Lin, J. J.*, Hsieh, S. H., & Golparvar-Fard, M. (2023). Automated vision-based construction progress monitoring in built environment through digital twin. Developments in the Built Environment, 100247. (SCI) ❐
A combination of Fig. 6 & Fig. 7.Integrated workflow for real-time construction progress monitoring and automatic schedule updates using AI, BIM, and robotic data collection.
This study introduced a closed-loop control framework for Digital Twin Construction (DTC) that leverages AI, BIM, and on-site image data to monitor construction progress in real time. Its key contribution is the full automation and predictive capabilities of progress tracking solutions in real-world construction settings. Visual data of real-world onsite progress is continuously synchronized with its digital counterpart. The resulting seamless feedback loop can detect deviations from the plan and support information-driven production control.
By aligning field performance with planning and scheduling, DTC can serve as a predictive monitoring solution which can support dynamic decision-making in the built environment.
Conference Highlights
Pal, A., Lin, J. J., and S. H. Hsieh (2023). “Automatic Alignment of Project Schedules and Reality Models for Construction Progress Updates,” Proceedings of ASCE International Conference on Computing in Civil Engineering (i3CE 2023), June 25-28, 2023, Corvallis, OR, USA.
Pal, A., T. H. Wang, Lin, J. J., and S. H. Hsieh (2021). “A Framework for Vision-based Progress Monitoring through Localization and Analysis of Unorganized Onsite Photographs,” Proceedings of the 26th Conference on Computer Applications in Civil and Hydraulic Engineering (CCACHE 2021), Paper No. 78, August 30-31, 2021, Taoyuan City, Taiwan.
Le, P. L., & Lin, J. J. (2023). Systematic Visual Data Capture Plans for Construction Monitoring using BIM. The 27th Conference on Construction Engineering and Management, July 13, Hsinchu, Taiwan (pp. 113).
Project Involvement within this field
運用深度學習及幾何模擬之模型驅動方法分析工程進度
Analyze project progress using model-driven methods using deep learning and geometric simulation.
2021.Feb – 2024.Feb. PI
Sponsor: National Science and Technology Council (NSTC)
由工地縮時攝影機佈置討論工程進度施作層級監控之系統化影像蒐集及分析
Develop the systematic image analysis for construction progress monitoring using the time-lapse camera on the construction site.
2021.Aug – 2022.Aug. PI
Sponsor: Brinno Inc.
工地攝影機管理及影像分析系統
Site Monitoring Camera and Analysis System.
2022.Oct – 2024.Oct. PI
Sponsor: Brinno Inc.