•  
  •  
 

Keywords

insulator string, color model, minimum external horizontal rectangular box, gray level cooccurrence matrix, mathematical morphology

Abstract

With the construction of smart grid, power companies gradually use unmanned aerial vehicles (UAV) to replace manual inspection of transmission lines. This paper proposes a method for processing aerial images of transmission line insulators captured by UAV. Firstly, the threshold and range of RGB components in the color model are used to segment the target and background areas. Secondly, mathematical morphology and nonoverlapping window texture features are applied to roughly mark the target area. Finally, a minimum circumscribed horizontal rectangular frame is generated. Then the texture features of all the patterns within the minimum circumscribed horizontal rectangular frame are identified to locate the minimum horizontal rectangular area of the aerial image of the insulator string. In the end, we use two images to verify the algorithm and compare with the algorithms in the literature. The results show that the algorithm proposed in this paper can better identify the position of insulator strings.

DOI

10.19781/j.issn.16739140.2020.04.002

First Page

13

Last Page

19

Download

Share

COinS