Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189287,
        author = {Rupanagudi Likhitha and Vinutha Prashanth and Thanushree M and Ruchitha P S and Hamsashree G P},
        title = {UAV Based Construction Monitoring And Inspection of Aerial/Side View Drone Based Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {7338-7347},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189287},
        abstract = {Automated monitoring of construction sites using unmannered aerial vehicle (UAV) imagery and deep learning technologies has emerged as a crucial innovation in modern construction management. This research presents an integrated framework that combines MobileNetV2, a lightweight Convolutional Neural Network (CNN), for construction stage classification, and YOLOv5, an advanced object detection algorithm, for personnel identification and safety monitoring. A Flask-based web application has been developed to interface with the system, allowing users to upload drone-captured images, visualize results, and generate analytical reports. The proposed system achieves high accuracy in stage classification (92.1%) and real-time personnel detection (mAP@0.5
= 0.87) using aerial datasets categorized into four stages: Foundation, Framing, Roofing, and Completed. Comparative evaluation against ResNet50 and EfficientNet-B0 highlights the superior computational efficiency of MobileNetV2. The research demonstrates a practical solution for real-time construction monitoring that minimizes manual inspection effort while improving accuracy and safety},
        keywords = {UAV, MobileNetV2, YOLOv5, Construction Monitoring, Deep Learning, Worker Safety, Computer Vision, Flask Application.},
        month = {December},
        }