Transformer bushing target detection method based on infrared image processing technology

Abstract

The invention provides a transformer bushing target detection method based on an infrared image processing technology. The method comprises the following steps: acquiring an infrared image of a transformer bushing in a transformer substation; identifying and extracting the transformer bushing in the infrared image by using a multi-template multi-matching method; extracting an ROI region, and segmenting the image of the region where the bushing is located for detection; carrying out filtering and denoising; carrying out semantic segmentation on the transformer bushing after image preprocessing, removing a background by using an OTSU algorithm, extracting an edge by using a Canny operator, removing a non-connected region by using morphological operation of an image, and segmenting a bushing base and an umbrella skirt part by using histogram binarization; and performing fine segmentation on each part of the transformer bushing to generate a temperature measurement reference datum line. According to the invention, the transformer bushing in a substation inspection infrared image can be rapidly and accurately extracted, and target detection and positioning can be carried out on the transformer bushing.

Description

technical field [0001] The invention belongs to the technical field of electric equipment image recognition, and in particular relates to a transformer bushing target detection method based on infrared image processing technology. Background technique [0002] With the continuous expansion of the scale of my country's power grid, the number and types of substation equipment have gradually increased, and the complexity of the network has increased, making its operation pressure increase, and safety hazards have also increased. Higher requirements have been put forward for its safe and reliable operation. Equipment inspection and detection is one of the important means to ensure the reliable operation of substation equipment. Due to the particularity of the equipment in the substation, in order to ensure the safety of the testing personnel, it is necessary to limit the observation and testing of the equipment from a safe distance; at the same time, in the relatively closed spac...

AI Technical Summary

Problems solved by technology

Due to the particularity of the equipment in the substation, in order to ensure the safety of the testing personnel, it is necessary to limit the observation and testing of the equipment from a safe distance; at the same time, in the relatively closed space of the substation, there are various and complex types of equipment, and many of them are live. In operation, so the observation angle of the substation equipment is limited

This makes the background complex in the field of view of the infrared image collected by the infrared detection equipment, the shooting distance and angle are limited, and the accuracy of the identification of the substation equipment is reduced. The quality of the collected infrared image will be significantly reduced, and the resolution of the infrared image will be reduced. This also makes the shortcomings of noise and low contrast of the infrared image more obvious, the edges of the image become blurred, and the details are seriously lost, so it brings great challenges to the identification of substation equipment in different states and positions. difficulty

Images