VBII-UAV: Vision-Based Infrastructure Inspection-UAV

Abdulla Al-Kaff, Francisco Miguel Moreno, Luis Javier San José, Fernando García, David Martín, Arturo de la Escalera, Alberto Nieva, José Luis Meana Garcéa

Abstract: Unmanned Aerial Vehicles (UAV) have the capabilities to undertake tasks in remote, dangerous and dull situations. One of these situations is the infrastructure inspection, at which, using the UAV decreases the risk and the operation time of the task comparing to a human inspector. Therefore, this paper presents a small vision-based UAV with the capability of inspection tasks of a civil and industrial infrastructure. The presented system is divided into three main algorithms; Depth-Color image correlation, Plane segmentation and distance estimation and Visual servoing. The system has been validated with real flight tests, and the obtained results show the accuracy of the system in both inspection measurements and the UAV maneuver controlling.