Air switch state detection method and device based on ORB feature matching and yolo

Abstract

The invention provides an ORB feature matching and yolk-based air switch state detection method. The method comprises the following steps: A, shooting an equipment image sample containing an air switch to establish a data set; B, carrying out training and exporting on a yolo model; C, manufacturing a standard template; D, shooting an equipment image containing the air switch to be detected, and performing ORB feature point extraction on the equipment image and generating a corresponding feature vector; E, performing feature matching to position the air switch to be detected, and correcting the equipment image in the step D; F, obtaining a to-be-detected switch image basically consistent with the standard template; G, inputting a to-be-detected switch image into the yolo model processed in the step B to obtain the number of switches and the state of each switch; and F, judging whether the air switch state is abnormal or not, and giving an alarm. The method is high in anti-interference performance, low in false detection rate, high in accuracy and capable of reducing the workload.

Description

technical field [0001] The invention relates to an air switch state detection method and device based on ORB feature matching and yolo. Background technique [0002] The stability of the power communication system directly affects the reliability and stability of the power grid operation, so the maintenance of power communication equipment is very important, and the air switch is a very important electrical appliance, which integrates control and multiple protection functions. The air switch can not only contact and break the circuit, but also protect the short circuit, severe overload and undervoltage of the circuit or electrical equipment. Therefore, the detection and maintenance of the air switch is an essential link in the power communication room. At present, manual detection or fixed camera monitoring is generally used in the detection of equipment in power communication equipment rooms. Both methods have defects: manual detection, due to the subjective factors of the ...

AI Technical Summary

Problems solved by technology

At present, manual detection or fixed camera monitoring is generally used in the detection of equipment in power communication equipment rooms. Both methods have defects: manual detection, due to the subjective factors of the personnel, can easily cause false detection, false detection or missed detection; fixed The detection method of camera monitoring has a limited detection range. When the number of devices to be detected increases, the detection cost will also increase. Moreover, the detection method of fixed camera monitoring mostly uses template matching algorithm for air switch status detection. This method is vulnerable to external environmental influences, its robustness is poor

Images