Electric Power ›› 2019, Vol. 52 ›› Issue (12): 39-45,53.DOI: 10.11930/j.issn.1004-9649.201812055

Previous Articles     Next Articles

Image Recognition of Icing Thickness of Transmission Line Based on Random Hough Transform

JIA Siqi1, LI Jun Hui1,2, DU Dongmei1, LIU Bin2, HE Qing1   

  1. 1. School of Energy Power and Mechanical Energy, North China Electric Power University, Beijing 102206, China;
    2. Power Transmission Project Institute, China Electric Power Research Institute, Beijing 100055, China
  • Received:2018-12-17 Revised:2019-01-31 Published:2019-12-05
  • Supported by:
    This work is supported by the National Natural Science Foundation of China (No.51678548).

Abstract: In order to improve the calculation accuracy of the thickness of the transmission line, the method of calculating the thickness of the transmission line based on random Hough transform is proposed. Firstly, the image of the line is grayscaled to remove the hue and color saturation; then the Canny operator is used to denoise the image and remove the image background, preserving only the foreground of the image; then using random Hough transform and least squares method to determine the straight line at the edge of the line; finally, the thickness of the ice is calculated based on the pixels of the line image before and after the icing. The calculation results show that the calculation accuracy of this method is 14% higher than that based on traditional Hough transform, which can significantly improve the monitoring accuracy and level of ice thickness of transmission lines.

Key words: transmission line, icing thickness, random Hough transform, image recognition

CLC Number: