Abstract:
Progress monitoring is crucial for effective project management, particularly in construction projects. The adoption of computer vision with deep learning expedites automation, accuracy, and efficiency in construction progress monitoring by overcoming the challenges of laborious, and error prone manual methods. While there is growing attention on developing computer vision based deep learning models for construction progress monitoring, deployment platforms for project managers are lacking. Using computer vision, this study develops a Mask Recurrent Convolutional Neural Network deep learning model. It utilizes progress images of drywall construction from two indoor construction sites and tests the model on a third indoor site in Sydney, Australia. The model is capable of automated as-built visual detection and work-in-progress measurement. The study also provides an understanding on the deployment process of the deep learning model on a cloud-based platform called Streamlit. By developing a model tailored for automatically quantifying work-in-progress of indoor construction elements and detailing the process of deploying that model on a cloud-based platform, this study significantly advances digitalization of construction project management. Project managers, stand to benefit from these advancements by gaining access to more accurate and automated construction progress monitoring for better decision-making.
