Authors:Juan Ignacio Larrauri Villamor, Gorka Sorrosal Yarritu, Mikel González Astorga
In this paper, we present a new automatic system in real time for overhead power line inspection by Unmanned Aerial Vehicle (UAV). The main contribution and novelty of this paper is focused on the design and development of an offline/online path planner through a new predictive model based on the cartographic and geodetic system. The environment of a power line inspection by UAV is static and known beforehand, therefore the flight planner could be designed offline and will automatically be updated during the flight inspection. This predictive model is used for achieving, by intelligent way, the best flight path and also will determine a priori the position and features of the electrical components to be reviewed and analyzed during the automatic flight inspection. The main purpose of the digital cartographic system is to provide the conversion of geographic information to spatial data. In order to realize the conversion from graphic maps to data, new artificial vision algorithms have been designed in this project to automatically extract the information from metadata files from GIS system. The output of data contains information about the position of electrical towers, insulators, roads, streets, railroad lines, rivers, wooded areas, isolated trees and obstacles along the power lines path. This paper is structured as follows. First section briefly introduces the current methods of inspection of overhead power lines. Second section describes our proposed system in detail. Third section present and discuss the experimental results. In the next section concludes our work with the conclusions. Finally, we cite the publications used in this paper.