Background difference and iteration searching-based status recognition method of high-voltage isolation switch

Abstract

The invention discloses a background difference and iteration searching-based status recognition method of a high-voltage isolation switch. The method sequentially includes the following steps: 1) taking a multi-frame consecutive image sequence, and taking intermediate values of pixel point grayscale values of corresponding positions in the multi-frame image sequence to use the same as grayscale values of corresponding pixel points in a background image to acquire the background image; 2) carrying out difference operating on a current-frame image and the background-frame image to obtain a foreground image; 3) processing the foreground image through a shadow suppression method, and marking a position of the high-voltage isolation switch; 4) tracking the position of the high-voltage isolation switch through iteration calculation when the position of the high-voltage isolation switch changes; 5) using a result of a previous frame as input to carry out cyclic iteration to acquire a motiontrajectory of the high-voltage isolation switch; and 6) analyzing status of the high-voltage isolation switch according to an included angle of a switch tracking point and a center line after the motion trajectory of the high-voltage isolation switch is acquired. The method is high in real-time performance, wide in an application range, stable and reliable.

Description

technical field [0001] The invention relates to the technical field of video detection, and more specifically relates to a method for identifying the state of a high-voltage isolating switch based on background difference and iterative search. Background technique [0002] The high-voltage isolating switch is mainly used for closing and breaking high-voltage lines, which ensures the safety of high-voltage electrical appliances and devices during maintenance work, and plays the role of isolating voltage. High-voltage isolating switches generally have an auxiliary switch positioning function based on mechanical principles, but this function is prone to positioning deviations when the machinery itself is rusted or worn, and line maintenance personnel are often required to confirm the switch status at the site of the isolating switch. Therefore, it is necessary to adopt remote video monitoring means to save labor costs and improve maintenance efficiency. [0003] At present, th...

AI Technical Summary

Problems solved by technology

The first is to upgrade the monitoring equipment, using high-speed infrared camera and other technologies, which can monitor the high-speed and clear images inside the high-voltage switch in real time, and can record, track, analyze and identify the video images for a long time. This method is costly. And the applicability is not strong

The other type is based on target detection technology, such as the Hough Forest algorithm. Such a technical solution often has a large amount of calculation, it is difficult to capture the switch state in real time, and it is easily affected by the environment number.

There is also a method of using modal analysis to realize switch state identification, which reflects the switch state by collecting multiple information such as vibration signals, temperature signals, and images of the switch. This method also has problems such as high cost and difficulty in wide application. , and because there are many devices involved, regular detection and adjustment are required to ensure the stable operation of each device

[0004] The methods of the prior art generally have the problems of high cost, insufficient robustness and insufficient application breadth

Therefore, there is an urgent need for an effective detection method to realize real-time monitoring of the state of the high-voltage isolating switch, and to prevent safety accidents caused by problems such as insufficient closure of the isolating switch and over-positioning.

Images