Automated progress monitoring of land development projects using unmanned aerial vehicles and machine learning
Journal
Automation in Construction
Journal Volume
168
Start Page
105827
ISSN
0926-5805
Date Issued
2024-12-01
Author(s)
DOI
10.1016/j.autcon.2024.105827
Abstract
In land development projects, effective control of the engineering progress is crucial for managing construction quality and costs. However, the conventional approach to monitoring progress is inadequate for large-scale projects. This paper proposes a technique that utilizes UAV images and machine learning techniques to monitor land development projects. The object detection and image segmentation techniques were used to detect essential construction objects. The detected objects were automatically compared to design drawings for checking the progress of the project. Moreover, to ensure personnel safety during construction, an automated process for identifying locations requiring safety barriers was also designed in the study. The effectiveness of all the proposed techniques was evaluated in a real case study. It is illustrated that this fully automated approach for land development monitoring is efficient and thus can contribute to construction safety, cost reduction, and quality assurance in a land development project.
Subjects
Image detection
Image segmentation
Land development
Machine learning
Unmanned aerial vehicles (UAVs)
Publisher
Elsevier BV
Type
journal article