Unmanned aerial vehicle (UAV) vision-based detection and location of power towers for transmission line maintenance
Unmanned aerial vehicle (UAV) vision-based detection and location of power towers for transmission line maintenance
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
- Author(s): R. Wang 1 ; S. Zhang 1 ; B. Chen 1 ; J. Xu 1 ; L. Zhong 1
-
-
View affiliations
-
Affiliations:
1:
State Grid Fujian Electric Power Company, Fuzhou, Fujian Province , P. R. China . ;
2: School of Electrical Engineering , Southeast University , No 2 Sipailou, Nanjing, Jiangsu Province 210096 , P. R. China
Source:
The 16th IET International Conference on AC and DC Power Transmission (ACDC 2020),
2021
p.
1937 – 1941
-
Affiliations:
1:
State Grid Fujian Electric Power Company, Fuzhou, Fujian Province , P. R. China . ;
- Conference: The 16th IET International Conference on AC and DC Power Transmission (ACDC 2020)
- DOI: 10.1049/icp.2020.0328
- ISBN: 978-1-83953-330-3
- Location: Online Conference
- Conference date: 02-03 July 2020
- Format: PDF
With the rapid development of technology in unmanned aerial vehicles (UAV), more and more UAVs are used by power supply companies for power line inspection and maintenance. However, a large quantity of aerial images captured by UAVs are processed manually at present, which relies on prior knowledge of power towers and is not only time-consuming but also inefficient. Worse still, the geographical positions of abnormal power towers are difficult to be obtained so that the maintenance team has no direction to proceed. In this work, we propose a deep learning-based method for detecting and locating abnormal power towers from the aerial images captured by UAVs. In this method, an objection detection algorithm based on deep convolutional neural network (CNN) is firstly designed to identify and detect abnormal power towers from aerial images. Secondly, the geographical positions of the detected abnormal power towers are approximated by UAV metadata recorded in aerial images (e.g. pixel size, altitude, pitch angle, roll angle, yaw angle, et al.) and several coordinate transformations. Compared with the classical image processing methods, the present method is automatic and end-to-end, and can be easily applied in the UAV based inspection of power transmission lines.
Inspec keywords: mobile robots; control engineering computing; autonomous aerial vehicles; meta data; maintenance engineering; deep learning (artificial intelligence); power transmission lines; power system control; convolutional neural nets; object detection; inspection; robot vision; poles and towers; power engineering computing
Subjects: Inspection and quality control; Control of electric power systems; Mobile robots; Power line supports, insulators and connectors; Optical, image and video signal processing; Computer vision and image processing techniques; Database management systems (DBMS); Neural nets; Power engineering computing; Power system control; Control engineering computing