The International Association for Automation and Robotics in Construction
Publications / 2022 Proceedings of the 39th ISARC, Bogotá, Colombia
Development of Framework for Highway Lawn Condition Monitoring using UAV Images
Planning, monitoring, and maintenance of highway assets is an essential, long-term operation for successful civil infrastructure management. These monitoring and maintenance activities are usually carried out manually, suffering from time-consuming, costly, potentially dangerous tasks. The advancements in Unmanned Aerial Vehicles (UAVs) and computer vision technologies have demonstrated the potential to enable automation of the monitoring workflows. Existing UAS-based approaches are used for various management; however, there was no study to examine the feasibility of aerial image-based computer vision algorithms for the purpose of lawn condition monitoring. This study aims to provide periodic and easy-to-use UAV technology for civil infrastructure maintenance. We developed the comprehensive framework from UAS data collection to build a deep learning model suitable to distinguish areas of interest with vague boundaries robustly, process the outputs into geo-database, and visualize them through a Geographic Information Systems (GIS) platform. The outcome of the proposed framework displays the overall mowing quality in the highway environment in an intuitive way to support decision-making in the management.