Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Power transmission line wire defect detection method based on machine vision

A power transmission line, machine vision technology, applied in the direction of neural learning methods, optical testing flaws/defects, instruments, etc., can solve the problem of shooting angles and scenes that are difficult to be universal, wires do not have segmentation and detection capabilities, and transmission lines operate normally Hidden dangers and other problems, to achieve the effect of state identification and defect location, improve practical performance, and reduce processing time

Active Publication Date: 2020-07-10
SOUTH CHINA UNIV OF TECH +1
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in outdoor scenarios, wires are easily affected by erosion and external damage, resulting in defects such as corrosion, wear, and wire breakage, which will cause great hidden dangers to the normal operation of transmission lines.
Some current methods for wire detection are mainly based on Hough transform and morphological image processing methods. On the one hand, it is difficult to be universal for changing shooting angles and scenes in outdoor scenes, and on the other hand, there is no segmentation for non-linear wires. and detection capabilities

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 transmission line wire defect detection method based on machine vision
  • Power transmission line wire defect detection method based on machine vision
  • Power transmission line wire defect detection method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described below in conjunction with specific examples.

[0054] Such as figure 1 As shown, the specific conditions of the machine vision-based transmission line conductor defect detection method provided in this embodiment are as follows:

[0055] Step 1: The UAV conducts fixed line inspections on the transmission line, and takes on-site images of high-voltage towers near the towers, such as figure 2 shown, and transmitted to the remote server over a long distance through the 4G network.

[0056] Step 2: Divide the on-site images collected by the drone into the training data set and the test data set in a ratio of 7:3, use Labelme software to mark the edges of the wires in the training data set, and obtain the label file of the corresponding image in json format , the annotation file includes the rectangular coordinate data of the wire target in the image, the mask point set data and category information, and the pictures and lab...

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 transmission line wire defect detection method based on machine vision, and the method comprises the steps: obtaining field image data, and making a training data set;constructing and training an instance segmentation network to obtain a prediction model; deducing an input picture by the model to obtain a rectangular region image and a binarized mask image of the wire; adopting a skeleton algorithm to extract a wire skeleton, calculating the average width of the wire, and reconstructing a binarized mask image; adopting a homomorphic filtering algorithm to eliminate the influence of uneven illumination of the rectangular area image, and combining a reconstructed binarization mask image to extract a segmented wire area image; generating a large number of rectangular frames on the wire area for screening; making a classification training data set, constructing and training a shallow classification network, and obtaining a classification prediction model; inputting the lead section area picture into the classification prediction model, and counting the defect type and defect proportion of the lead section state. The method can accurately segment the wire, detect the state of the wire in a segmented manner, and judge the defect type and defect degree of the wire.

Description

technical field [0001] The invention relates to the technical field of defect detection of transmission line conductors, in particular to a method for detecting defects of transmission line conductors based on machine vision. Background technique [0002] The safety of transmission line conductors is related to whether the power can be transmitted normally. The conductors are equivalent to the blood vessels of the power grid system and are used to transmit and distribute power. However, in outdoor scenarios, wires are easily affected by erosion and external force damage, resulting in defects such as corrosion, wear, and wire breakage, which will cause great hidden dangers to the normal operation of transmission lines. Some current methods for wire detection are mainly based on Hough transform and morphological image processing methods. On the one hand, it is difficult to be universal for changing shooting angles and scenes in outdoor scenes, and on the other hand, there is n...

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
IPC IPC(8): G06T7/00G06T7/11G06K9/38G06K9/62G06N3/04G06N3/08G01N21/88
CPCG06T7/0004G06T7/11G06N3/08G01N21/8851G06T2207/20081G06T2207/20084G01N2021/8887G01N2021/8874G01N2021/8854G06V10/28G06N3/045G06F18/241G06F18/214Y04S10/50
Inventor 杜启亮黎春翔田联房邝东海
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products