GIS equipment defect detection method and system based on DSPN, terminal and medium

• Main Authors: XIAO WEI, LUO BING, WANG TINGTING, ZHANG HAOFENG, WEN YONGHUA, LIU GUOTE
• Format: Patent
• Language: Chinese; English
• Published: 19.04.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention is suitable for the technical field of power system fault detection, and provides a DSPN-based GIS equipment defect detection method and system, a terminal and a medium, and the method comprises the steps: obtaining a to-be-detected defect image, inputting the to-be-detected defect image to a deep neural network model, generating a defect detection image, and carrying out the detection according to the defect detection image, and determining defect detection result information. The method can make full use of the potential features of the feature maps, enables the interested information to act on the output feature maps of different sizes through the space and channel weights of different scales, effectively improves the attention of the network to the global information of the X-DR image, effectively enhances the expression capability of the model, effectively aims at the features of imaging blurring of GIS equipment in the X-DR image, and improves the reliability of the X-DR image. And the def