Overhead Power Line Clearance Inspection using an Unmanned Aerial Vehicle
Nearly everyone is nowadays dependent on electric power. This power is provided to most major cities by overhead power lines spanning wide areas that have to resist harsh outdoor conditions. To ensure the functionality of these critical infrastructures, mostly endangered by growing vegetation, regular inspections are required. Today this is done using an inspector on a helicopter or an inspector from the ground who estimates the vegetation growth using a binocular. These are only very coarse maintenance approaches and are on the one hand very costly and on the other hand very time consuming. In addition a proper automatic documentation is not possible with the just mentioned methods.
In the project FreeLine we develop an automated system that acquires airborne imagery using an unmanned aerial vehicle (UAV). These images are used to metrically reconstruct the power line including its environment. By semantic classification of the components of the reconstruction and having a metric scale, undercuts of the clearance distance between the power line and surrounding vegetation can be detected and highlighted for further maintenance work. Further, the acquired data serves as basis for simulation. This includes the extent of the power lines at different load and ambient temperature.
FreeLine is a collaborative research project at Graz University of Technology (Austria), funded by the Austrian Research Promotion Agency (FFG) and OMICRON electronics GmbH as Bridge1 project 843450.
M. Maurer, M. Hofer, F. Fraundorfer, and H. Bischof, “AUTOMATED INSPECTION OF POWER LINE CORRIDORS TO MEASURE VEGETATION UNDERCUT USING UAV-BASED IMAGES,” in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences , 2017. [PDF]
Wir verwenden Cookies, um Ihnen in Zukunft weiterhin das bestmögliche Service zur Verfügung stellen zu können. Nähere Informationen sowie Widerrufsmöglichkeiten finden Sie in der Datenschutzerklärung. Präferenzen speichern