Transmission Line Identification under Complex Background Based on Gray Filtering

Abstract

The complex background causes great interference to the visual recognition of transmission lines. Therefore, a transmission line extraction algorithm which performs well in complex background is urgently needed. This paper uses grayscale iterative filtering to achieve this purpose. Firstly, grayscale processing is performed to obtain a grayscale image that filters out color and brightness interference. Then an improved OTUS algorithm is proposed to remove complex background interference and a gradient enhancement algorithm is used to enhance the contrast between the transmission line and the background. Finally, using Canny edge detection algorithm to extract the edges of the image, then using morphological processing to optimize the Hough transform effect and finally extract the transmission lines. The results show that the proposed algorithm can effectively extract transmission lines under the complex background.