Electric power inspection image identification method

A technology of image recognition and power inspection, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as slow recognition speed, insulators cannot be accurately identified and positioned, and a large amount of calculation

Inactive Publication Date: 2021-03-26
ZHENJIANG COLLEGE
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a power inspection image recognition method, based on the YOLOv4 (YOU ONLY LOOKONCE) target detection method to perform target feature extraction and recognition, to solve the problem of small volume in the prior art under the conditions of dim light and complex background. Insulators cannot be accurately identified and positioned, and the amount of calculation is large, which consumes a lot of computing resources and the identification speed is slow.

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
  • Electric power inspection image identification method
  • Electric power inspection image identification method
  • Electric power inspection image identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below with reference to the accompanying drawings and specific examples.

[0049] Such as figure 1 As shown, the power inspection image recognition method includes the following steps:

[0050] 1) The foreground field is imaged on the left and right cameras, forming the left and right chart, collecting the left and right camera images, calibrate the camera to obtain the parameter matrix, distortion coefficient matrix, intrinsic matrix, base matrix, rotation matrix, and translation matrix;

[0051] 2) Processing the video to obtain a frame map, using an active illumination image enhanced method to preprocess the obtained image, including the following steps:

[0052] 1 Use the depth of field to divide the image into prospects and background area;

[0053] 2 On the basis of the depth of field, the insulator is separated from the background by gradient information according to the insulator and the background;

[0054] 3 Select th...

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 an electric power inspection image identification method, which comprises the following steps: calibrating a camera, processing a video to obtain a frame image, preprocessing the obtained image by adopting an image enhancement method based on active illumination, carrying out target identification on an insulator image based on a YOLOv4 network target detection method, andperforming insulator extraction, namely insulator feature extraction. According to the method, feature matching operation is only carried out on the pre-selected frame image, so that the size of the image in the image is reduced, the calculation efficiency is greatly improved, and a beneficial effect is achieved for improving the real-time performance of target detection. According to the invention, defect identification is carried out on the insulator in an inspection image containing a complex background in a real environment, and reliable technical support is provided for a power grid maintenance department.

Description

Technical field [0001] The present invention relates to a power inspection image identification method, which belongs to the field of image processing recognition. Background technique [0002] With the rapid development of the national economy, people's dependence and demand for electrical energy are increasing, and the power inspection tasks brought about by this are increasing. In recent years, the improvement of science and technology levels has gradually replaced the traditional artificial patrol mode, and these emerging patrols improve work efficiency and safety performance to a certain extent. However, the market is complicated, and there are a wide variety of inspection images, which still brings great challenges to the relevant maintenance departments. As artificial intelligence and image technology continue to develop and mature, smart recognition of power devices defects is possible. [0003] In the power device, insulator is a huge and extremely important part of the ...

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): G06T7/00G06T7/11G06T7/136G06T7/194G06T7/80G06T7/90G06T5/30G06T5/40G06T3/00
CPCG06T3/0075G06T5/30G06T5/40G06T7/0004G06T2207/20032G06T2207/20036G06T2207/20081G06T2207/30164G06T2207/30244G06T7/11G06T7/136G06T7/194G06T7/80G06T7/90
Inventor 徐沛
Owner ZHENJIANG COLLEGE
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