Real-Time On-Board Deep Learning Fault Detection for Autonomous UAV Inspections

Naeem Ayoub*, Peter Schneider-Kamp

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

61 Downloads (Pure)

Abstract

Inspection of high-voltage power lines using unmanned aerial vehicles is an emerging technological alternative to traditional methods. In the Drones4Energy project, we work toward building an autonomous vision-based beyond-visual-line-of-sight (BVLOS) power line inspection system. In this paper, we present a deep learning-based autonomous vision system to detect faults in power line components. We trained a YOLOv4-tiny architecture-based deep neural network, as it showed prominent results for detecting components with high accuracy. For running such deep learning models in a real-time environment, different single-board devices such as the Raspberry Pi 4, Nvidia Jetson Nano, Nvidia Jetson TX2, and Nvidia Jetson AGX Xavier were used for the experimental evaluation. Our experimental results demonstrated that the proposed approach can be effective and efficient for fully automatic real-time on-board visual power line inspection
Original languageEnglish
Article number1091
JournalElectronics
Volume10
Issue number9
Number of pages14
ISSN2079-9292
DOIs
Publication statusPublished - 2021

Bibliographical note

Funding Information:
Funding: The presented research was supported by the Innovation Fund Denmark, Grand Solutions, under Grant Agreement No. 8057-00038A Drones4Energy project.

Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords

  • Autonomous Drones Systems
  • Deep Learning
  • Fault Detection
  • Power Lines Inspection

Fingerprint

Dive into the research topics of 'Real-Time On-Board Deep Learning Fault Detection for Autonomous UAV Inspections'. Together they form a unique fingerprint.

Cite this