This work aims to develop a web platform for inspecting roof structures for technical assistance supported by drones and artificial intelligence. The tools used were HTML, CSS and JavaScript languages; Firebase software for infrastructure; and Custom Vision for image processing.
This study adopted the design science research approach, and the main stages for the development of the web platform include (1) creation and validation of the roof inspection checklist, (2) validation of the use of Custom Vision as an image recognition tool, and (3) development of the web platform.
The results of automatic recognition showed a percentage of 77.08% accuracy in identifying pathologies in roof images obtained by drones for technical assistance.
This study contributed to developing a drone-integrated roof platform for visual data collection and artificial intelligence for automatic recognition of pathologies, enabling greater efficiency and agility in the collection, processing and analysis of results to guarantee the durability of the building.
