Insulator icing detection method based on GLOH descriptor and GVF-Snake model

Abstract

The invention discloses an insulator icing detection method based on a GLOH descriptor and a GVF-Snake model. The method comprises steps that 1, an input image is pre-processed; 2, a target area of interest is extracted, and the area contains the insulator information; 3, the GLOH descriptor is utilized to position an insulator; 4, the GVF-Snake model is utilized to precisely detect insulator contour; and 5, the insulator contour is analyzed, whether the insulator is in an icing state is determined through calculating the maximum radial distance, and icing thickness is calculated under the icing condition. The method is advantaged in that a problem of difficulty in distinguishing the insulator from the complex background existing in a traditional method can be solved, and insulator icing condition determination accuracy can be effectively improved.

Description

technical field [0001] The invention relates to the fields of power system, pattern recognition and classification, especially the classification and detection of specific targets. Background technique [0002] In the power system, icing on insulators has always been a great threat to the security of the power grid. Especially in the cold winter, insulators are often covered with icing, and icing flashover is a frequent hazard in transmission lines, which poses a great safety hazard to the insulation of the line and the safe operation of the system. Therefore, It is of great significance to detect icing on insulators. With the development of machine vision technology and image processing technology, the use of vision and image processing technology to detect the state of insulators and automatically identify the icing of insulators plays a very important role in ensuring the safe operation of power systems. [0003] Recently, researchers have proposed many algorithms for i...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the defect that the traditional method is difficult to completely separate the insulator from the complex background, the present invention provides an insulator icing detection algorithm based on the GLOH descriptor and the GVF-Snake model, in order to accurately and automatically locate the insulator, thereby effectively improving the performance of the insulator. Accuracy of Icing Condition Judgment

Images