Insulator string drop detection method and device

Abstract

The invention provides a method and a device for detecting a string drop of an insulator, and relates to the technical field of image processing. The insulator drop string detection method is applied to electronic equipment, and the method includes: obtaining an image including the insulator to be detected captured by a drone; extracting a target area including the insulator to be detected in the image; Classification to obtain a first output value; according to the comparison result between the first output value and a preset first threshold value, it is determined whether a string failure occurs in the insulator to be detected. The insulator drop detection method and device provided by the present invention can detect whether the insulator in the transmission line has a drop failure in a complex and changeable application background, and the accuracy rate of detecting whether the insulator in the transmission line has a drop failure is high. It can be widely used in the detection of insulator string drop in the actual inspection operation.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for detecting insulator string drop. Background technique [0002] The transmission line is responsible for the transmission of electric energy, which plays a vital role in the safe and reliable operation of the power grid and directly affects the stable development of the national economy. Among the many devices in the transmission line, the number of insulators is huge, and they play an important role in insulation and providing mechanical support. Once a fault occurs, the power supply of the entire transmission line will be interrupted, and even a large area will be blacked out, resulting in huge economic losses. . However, the long-term operation of transmission lines in the wild is greatly affected by natural factors and climate, and insulators are prone to string drop failures. [0003] The traditional image insulator string detection method i...

AI Technical Summary

Problems solved by technology

However, it is often very difficult to select description features with strong robustness and accuracy. Such artificial features are difficult to guarantee the invariance of rotation, scale, and translation of images in the actual inspection environment, and they often fail for complex and changeable application backgrounds. The effect of the actual inspection operation is poor

Images