Power equipment infrared image detection method and system based on deep learning

A technology for power equipment and infrared images, which is applied in the field of infrared image detection of power equipment based on deep learning, can solve problems such as the detection accuracy of infrared images of difficult power equipment, and achieve the effects of saving manpower, high detection accuracy, and improving detection accuracy.

Pending Publication Date: 2022-05-10
STATE GRID HUNAN ELECTRIC POWER +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Technical problem to be solved by the present invention: Aiming at the above-mentioned problems of the prior art, a method and system for detecting infrared images of power equipment based on deep learning are provided. The present invention can solve the problem that existing methods are difficult to improve complex scenes on the basis of ensuring real-time performance The problem of the detection accuracy of infrared images of electric power equipment, the detection accuracy of electric power equipment is high, can save manpower, and achieve the purpose of increasing efficiency and energy saving

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Power equipment infrared image detection method and system based on deep learning
  • Power equipment infrared image detection method and system based on deep learning
  • Power equipment infrared image detection method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] This embodiment provides a method for detecting infrared images of power equipment based on deep learning, including collecting infrared images of detected power equipment, inputting infrared images of power equipment into a pre-trained infrared image classification model of power equipment to obtain the detected power equipment test results, such as figure 1 As shown, the power equipment infrared image classification model includes:

[0028] The backbone feature extraction network is used to extract different levels of features from the input infrared images of power equipment;

[0029] Strengthen the feature extraction network FDAN, which is used to enhance the low-level features extracted by the backbone feature extraction network based on the double attention module DAM;

[0030] The detection head network is used to perform detection based on the enhanced features to obtain the detection results of the electric equipment.

[0031] The backbone feature extraction ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a power equipment infrared image detection method and system based on deep learning, and the method comprises the steps: collecting a detected power equipment infrared image, inputting the power equipment infrared image into a pre-trained power equipment infrared image classification model, and obtaining a detection result of the detected power equipment, the power equipment infrared image classification model comprises a trunk feature extraction network used for extracting features of different levels; the enhanced feature extraction network FDAN is used for performing feature enhancement on the low-level features extracted by the trunk feature extraction network based on a double attention module DAM; and the detection head network is used for carrying out detection based on the feature after feature enhancement to obtain a detection result of the power equipment. The method can solve the problem that it is difficult to improve the detection precision of the infrared image of the power equipment in a complex scene on the basis of guaranteeing the real-time performance in an existing method, the detection precision of the power equipment is high, manpower can be saved, and the purposes of efficiency improvement and energy conservation are achieved.

Description

technical field [0001] The invention relates to an image detection technology of electric power equipment, in particular to a deep learning-based infrared image detection method and system for electric power equipment. Background technique [0002] With the rapid development of social demand for electricity, the modern power system is gradually developing in the direction of large power grid, large capacity, and ultra-high voltage. Detection, in order to prevent serious accidents caused by power equipment failure and paralysis of the power system. Now infrared thermal imaging technology is widely used in the detection of electric power equipment. The infrared thermal imager scans and takes pictures of the electric equipment to obtain the infrared image of the equipment. The number of infrared images is increasing rapidly, which will not only consume a lot of manpower, but also cannot accurately and efficiently identify and locate power equipment by manpower alone. [0003]...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06K9/62G06N3/04G06N3/08G06V10/40G06V10/764G06V10/774G06V10/82
CPCG06T7/0004G06N3/08G06T2207/10048G06T2207/20081G06T2207/20084G06T2207/30108G06N3/045G06F18/241G06F18/214
Inventor 蔡杰张华驿肖宇刘星毋靖轩郑权国
Owner STATE GRID HUNAN ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products