Substation foreign matter identification and detection method, device and system

Abstract

The invention provides a substation foreign matter identification and detection method, device and system, and relates to the technical field of target detection, and the method is executed through an improved target detector. The improved target detector comprises a backbone network, a feature fusion network and a classification identification network which are connected in sequence; the method comprises the steps of obtaining a to-be-detected image for a transformer substation; performing feature extraction on the to-be-detected image through the backbone network of the target detector to obtain a feature map of the to-be-detected image, wherein the backbone network comprises a first preset number of dilated convolution residual error sub-networks which are connected in sequence; performing feature fusion on the feature map of the to-be-detected image based on a feature fusion network to obtain fused feature information; and performing target detection on the fusion feature information based on a classification identification network so as to identify and detect the foreign matters of the transformer substation. According to the invention, the accuracy and robustness of foreign matter identification of the target detector in the transformer substation are improved.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a method, device and system for identifying and detecting foreign objects in substations. Background technique [0002] The substation is an important part of the power grid and the core node in power transmission. The substation is located in a complex environment and is easily attacked by foreign objects. Substation inspection is an integral part of power inspection operations. Typical foreign objects in substations include bird nests, waste plastic films, kites, balloons, honeycombs, dust screens, etc. There are many kinds of foreign objects in substation foreign object recognition, there are huge differences in the target scale of foreign objects, and the environment of the substation is complex. At present, the commonly used object detection methods are roughly divided into two categories: one-stage detector and two-stage detector. [0003] However, in the detect...

AI Technical Summary

Problems solved by technology

[0003] However, in the detection of foreign objects in substations, one-stage detectors and two-stage detectors usually only use the backbone network of the classification task, resulting in poor target localization ability of object detectors, resulting in poor detection accuracy of foreign objects in substations. Low

Images