Power equipment image detection method and device, power equipment and storage medium

Abstract

The embodiment of the invention discloses a power equipment image detection method and device, power equipment and a storage medium. The power equipment image detection method comprises the steps: constructing a first training set based on sample defect pictures; training a preset neural network model by using the first training set to obtain a defect detection model; classifying the to-be-detected pictures according to a preset method to obtain defect pictures; and identifying the defect picture through the defect detection model so as to determine the defect category and the defect positionof the defect picture. By automatically detecting a huge amount of power equipment pictures generated by inspection equipment in a power system, automatically classifying the pictures based on an automatic detection result to select defect pictures and automatically mark defect positions of the defect pictures, the identification efficiency and the identification accuracy of the pictures are improved, and the problems of low efficiency and low recognition accuracy caused by manual recognition and picture defect marking in the prior art are solved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of electrical equipment operation and maintenance, and in particular, to an image detection method and device for electrical equipment, electrical equipment, and a storage medium. Background technique [0002] In recent years, with the continuous development of digital camera and robot technology, newly built smart substations and some transformed unattended substations realize efficient substation inspections through video surveillance or robots equipped with cameras, and transmit on-site image data to the monitoring center Perform manual analysis and identification. [0003] The existing image and video data have a large stock and a fast growth rate. There are many types of specific defects in substation equipment during the inspection, and the number of images generated by the inspection is large. At present, it is mainly relying on manual recognition of these images to find out ...

AI Technical Summary

Problems solved by technology

[0003] The existing image and video data have a large stock and a fast growth rate. There are many types of specific defects in substation equipment during the inspection, and the number of images generated by the inspection is large. At present, it is mainly relying on manual recognition of these images to find out the specific defect location of the defect pictures. , there are problems of low efficiency and low recognition accuracy

Images