Open AccessThe Detection Algorithm of Broken Wires in Power Lines Based on Grabcut Segmentation
Author(s) -
Jiayi Guo,
Xuexun Guo,
Limin Wang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/7/072017
Subject(s) - ransac , segmentation , power (physics) , line (geometry) , artificial intelligence , computer science , algorithm , aerial image , image segmentation , computer vision , line segment , fault (geology) , pattern recognition (psychology) , image (mathematics) , mathematics , physics , geometry , quantum mechanics , seismology , geology
Unmanned aerial vehicle (uav) has the advantage of rapid and efficient in power line fault detection. However, the background of power line image taken by uav is complex, and it is difficult to extract the foreground power line for fault detection.Aiming at this problem, we propose an algorithm based on Meanshift superpixel segmentation and Grabcut for further segmentation optimization. At the same time, the RANSAC algorithm is used for denoising to extract accurate power lines. Finally, the power lines are constrained based on their slender characteristics. Compare the width change on the same wire to detect the occurrence of strand breakage in the power line. The experimental results show that the algorithm has a good effect on the detection of broken strands in power lines.