The Orientation Angle Detection of Multiple Insulators in Aerial Image - Advances in Image and Graphics Technologies - page 294

The Orientation Angle Detection of Multiple Insulators
in Aerial Image *
Zhenbing Zhao, Ning Liu, Mingxiao Xi, and Yajing Yan
School of Electrical and Electronic Engineering, North China Electric Power University,
Baoding, 071003, China
{zhaozhenbing2002,15075230864,
yanyajing1013}@163.com,
[e-mail]
Abstract. Insulator is one of the important equipments on the transmission line,
and its orientation angle detection is an important preprocessing step for accu-
rate localization of insulator. This paper proposes a method of orientation angle
detection of insulators in order to realize the orientation determination of mul-
tiple insulators in aerial image with complicated background. Firstly, extract
sequential edge points and define their orientation angles of each linking con-
tour in the preprocessed image. And secondly define the points with sign-
Changing angle as candidate points. Finally, the accurate points can be picked
up by RANSAC (RANdom SAmple Consensus) from candidate points, and the
straight line which accurate points locate in is the main direction of the target.
Experimental results verify that the proposed method has higher detection accu-
racy compared with the existing methods that can lay the foundations for the lo-
calization of multiple insulators in complicated background.
Keywords: Orientation angle detection, multiple insulators, aerial image,
complicated background, RANSAC.
1 Introduction
Insulator is indispensable equipment in the power system with the dual function of
electrical insulation and mechanical support [1,2]. And the localization of insulator for
monitoring its status is very necessary to avoid causing a failure of flashover and
breakdown. The problem of insulators' orientation angle detection is finding the cor-
rect orientation so that the insulator would be in an upright position which makes insu-
lators' localization easier and more accurate in aerial image with complex background.
There are a lot of methods of target orientation angle detection.
Literature [3,4] proposes a method that estimates the target aspect angular making
use of track tracking. This method can realize the orientation angle estimation
of moving target with high precision, but for still image, it may be helplessness.
* The research is supported by “The Fundamental Research Funds for the Central Universities”
under grant number 12MS122.