Related Experiment Video
Updated: Oct 22, 2025
08:25
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
Published on: May 7, 2019
9.2K
Evaluating the Work Productivity of Assembling Reinforcement through the Objects Detected by Deep Learning.
Jiaqi Li1, Xuefeng Zhao1,2, Guangyi Zhou1,3
1Faculty of Infrastructure Engineering, Dalian University of Technology, Dalian 116024, China.
Sensors (Basel, Switzerland)
|August 28, 2021
Summary
This study introduces a computer vision method to evaluate reinforcement assembly productivity in construction using deep learning. The approach accurately tracks workers and objects, enabling efficient productivity assessment without worker interference.
Area of Science:
- Construction Engineering
- Computer Vision
- Deep Learning
Background:
- Deep learning and computer vision are increasingly used in engineering construction.
- Few computer vision methods exist for evaluating work productivity in construction.
Purpose of the Study:
- To propose a computer vision-based method for evaluating reinforcement assembly productivity.
- To utilize deep learning for object detection and productivity analysis in super high-rise projects.
Main Methods:
- Developed a CenterNet-based detector (DLA34 backbone) for distinguishing reinforcement assembly entities with high accuracy (mAP 0.9682) and speed (0.076 s/image).
- Applied the detector to video frames to identify workers and objects, determining worker count and task duration via coordinate analysis.
- Evaluated productivity using the number of workers and time spent on the task.
Main Results:
- The developed detector achieved high performance in identifying construction elements.
- Productivity evaluation results from four validation videos showed consistency with actual construction conditions.
- The method successfully linked construction workers to work objects for productivity assessment.
Conclusions:
- The proposed computer vision method enables effective productivity evaluation in reinforcement assembly.
- This approach enhances construction management efficiency by providing objective productivity insights.
- The method establishes a non-intrusive link between workers and tasks, improving management oversight.
