Related Experiment Video
Updated: Jul 8, 2026
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
1.0K
Development of advanced progress recognition algorithms for construction monitoring
Lai Yingdong1, Lin Zhijun1, Ye Zhijie2
1Jiangmen Power Supply Bureau of Guangdong Power Grid Co., Ltd., Jiangmen, Guangdong, China.
Plos One
|October 9, 2025
Summary
This study introduces an automated Construction Progress Monitoring (CPM) system using YOLOv8 object detection. The novel approach enhances efficiency and accuracy, offering a reliable alternative to traditional manual methods.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Construction Management
Background:
- Traditional Construction Progress Monitoring (CPM) relies on manual, labor-intensive methods prone to errors and delays.
- Existing CPM techniques lack the efficiency and accuracy required for modern construction projects.
Purpose of the Study:
- To develop and validate an automated CPM system utilizing the YOLOv8 object detection algorithm.
- To enhance the efficiency, accuracy, and cost-effectiveness of construction progress monitoring.
Main Methods:
- YOLOv8 object detection algorithm was implemented for real-time identification and tracking of construction elements.
- A custom dataset of 768 labeled images depicting window installation stages was created for model training and validation.
Main Results:
- The YOLOv8 model achieved high performance metrics: mAP@50 of 0.953, mAP@50-95 of 0.678, precision of 0.91, and recall of 0.88.
- The automated system demonstrated reliable, efficient, and cost-effective progress monitoring capabilities.
Conclusions:
- The integration of computer vision, specifically YOLOv8, offers a significant advancement over traditional CPM methods.
- This automated approach facilitates timely decision-making and contributes to the successful completion of construction projects.
