Power equipment infrared image recognition method based on regional convolutional neural network

A convolutional neural network, infrared image technology, applied in the field of computer image processing and deep learning, can solve the problems of false detection and missed detection, low detection efficiency, etc., to overcome low detection efficiency, simple detection, and overcome false detection and leakage. Check the effect

Pending Publication Date: 2021-11-02
NORTHEAST DIANLI UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above problems, the present invention's method of infrared image recognition of power equipment based on regional convolutional neural network is proposed to solve the problems of low detection efficiency, false detection and missed detection in the current manual inspection process.

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 recognition method based on regional convolutional neural network
  • Power equipment infrared image recognition method based on regional convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] refer to figure 1 As shown, the infrared image recognition method for power equipment based on the regional convolutional neural network provided by the embodiment of the present invention includes:

[0026] S100. Obtain infrared images of various electrical equipment under different environmental conditions, and construct an infrared image sample library of electrical equipment; each infrared image is labeled with electrica...

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 recognition method based on a regional convolutional neural network, and the method comprises the steps of firstly obtaining infrared images of various power equipment under different environment conditions, constructing a power equipment infrared image sample library, and providing a sample set for the training of a neural network; in the recognition process, firstly, inputting an infrared image with an electric power equipment label into a ZF network for feature extraction, and obtaining a feature map of an electric power equipment image; generating a suggestion window through a Faster-RCNN for the obtained feature map of the image of the power equipment, and predicting related parameters of an anchor point through the Faster-RCNN by using the feature map to obtain an object frame finally output by the power equipment in the infrared image; and using the Softmax Loss and the Smooth L1Loss to complete the classification and the positioning of the infrared image of the power equipment. The method can output a visual, safe and reliable identification result with accurate analysis, and overcomes the inevitable defects of low detection efficiency, false detection and missing detection in the traditional manual inspection process.

Description

technical field [0001] The invention relates to the field of computer image processing and deep learning, in particular to an infrared image recognition method for electric power equipment based on a regional convolutional neural network. Background technique [0002] The safe operation of power equipment in the power system is the basis for ensuring the reliable operation of the power grid. At present, the diagnosis of electrical equipment has been widely used infrared targeting technology to complete. The fault detection method of electrical equipment based on infrared thermal imager has the characteristics of intuitive diagnosis, safety and reliability, and accurate analysis. Since the equipment diagnosis process using thermal imaging cameras still requires on-site inspection by operation and maintenance personnel, it is inevitable that there will be problems of low detection efficiency, false detection and missed detection during the manual inspection process. Therefor...

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): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08G06Q50/06
CPCG06N3/08G06Q50/06G06N3/045G06F18/2415
Inventor 吴君鹏李相磊周一博
Owner NORTHEAST DIANLI UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap