Abstract
In low voltage distribution network, the conductor length of overhead line is needed to build the physical topology and estimate the electrical parameters. However, the overhead lines are erected on the pole and the line trend is complicated, so the conductor length is not easy to be measured directly. This paper presents a non-contact measurement method of overhead conductor length based on insulator target recognition and location by image processing. In the large scene image taken by unmanned aerial vehicle(UAV), the insulator targets on low voltage overhead line are small and have weak characteristics. We will partition the large scene image into manageable cutouts to avoid missed detection of the small insulator targets. The attention mechanism module with channel attention and spatial attention is introduced to give attention weight to the characteristic elements in the region of interest, so as to identify the small insulator targets quickly and effectively. On the basis of small insulator targets recognition, the relationship of coordinates in the UAV image system is established according to the machine vision principle. The longitude and latitude of the insulators and the conductor length of the overhead lines are estimated through the conversion relationship between coordinate systems. Finally, the experiments of the overhead line pictures taken by the UAV are carried out. Compared with the manually measured overhead conductor length, the results show that the method in this paper is effective and has high precision.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.