ANALYSIS OF TRANSMISSION LINE LINEARITY USING HOUGH TRANSFORM
Abstract
Transmission lines perform the most important part that is to transfer electric power from the generating station to load centers. An overhead transmission line is one of the main components in every electric power system. Faults in transmission line (lagging line) have led to several collaborative efforts between industry and academia to research different approaches, with focus on automating the inspection task. Recently, the demand for electrical power has invariably affected the need for more national grids and transmission lines. Since transmission lines are one of the major components of an electrical power system, these lines must be protected and tracked from time to time to avoid or mitigate the faults- either transient or permanent that ensue from significant problems that transmission lines suffer.
This paper is a contribution towards autonomous aerial capturing of the power line infrastructure. More specifically, the problem of tracking of straight transmission lines from the captured images. This work develops a system for detecting lagging and discontinuity in transmission lines. The aim of this project is to analyze the linearity of Transmission lines using Hough Transform, The Unmanned Aerial Vehicles flies at an altitude to capture images of the transmission line. The captured images are preprocessed. At this stage the images are acquired and are prepared for line detection reducing any unwanted noise that may douse the accuracy. Gray scale conversion was done to simplify processing steps. The converted image then undergoes edge detection implementation using the Canny edge detection algorithm. An accumulator array that will store the voting information is then created being the first step in implementing the Hough Transform, Hence the voting process. After this process, Line detection and line tracking are implemented. To then evaluate the performance of the system, a dataset of appropriate characteristics is chosen. The developed system was implemented in MATLAB.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.