Deep learning-based insulator identification method

A technology of insulator recognition and deep learning, applied in scene recognition, character and pattern recognition, instruments, etc., can solve the problems of lack of universality, inability to use well, and many background changes, to reduce the number of parameters and improve the quality of life. Noise effect, the effect of improving the signal-to-noise ratio

Active Publication Date: 2017-09-08
GUIZHOU POWER GRID CO LTD
View PDF4 Cites 57 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The background changes a lot and is relatively complicated. The above

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
  • Deep learning-based insulator identification method
  • Deep learning-based insulator identification method
  • Deep learning-based insulator identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] Example: such as Figure 1-5 As shown, an insulator identification method based on deep learning, the method includes the following steps:

[0056] Step 1, preprocessing the original image of the aerial photography, detecting whether there is a problem of shaking or blurring in the captured image, and performing denoising and anti-shaking processing;

[0057] Step 2, sample expansion, on the basis of preprocessing the image in step 1, by using multiple rotations, noise perturbation, and changing the contrast of the image to the image, multiple similar images are generated to expand the sample;

[0058] Step 3. Collect samples. According to the different materials of insulators, mainly collect ceramic insulators, glass tempered insulators, synthetic insulators, and semiconductor insulators. In the process of sample collection, ensure that the number of samples of each type of insulator is greater than 1000. The total number Not less than 4000

[0059] Step 4, training ...

Embodiment 2

[0075] Embodiment 2: a kind of insulator identification method based on deep learning, this method comprises the following steps:

[0076] Step 1: First, preprocess the road image. Due to the influence of shooting conditions, ground oil pollution, CCD noise, human and other factors during the acquisition of road surface images, noise interference will be generated on the acquired road surface images. Therefore, the original image is denoised first, which can improve the signal-to-noise ratio of the image, effectively enhance the target features, suppress part of the background noise, and enhance the contrast between the target and the background. Conventional algorithms for denoising processing may produce blurring effects on the edge of the target. The embodiment of the present invention performs denoising processing based on bilateral filtering. It can not only remove noise, but also achieve a good denoising effect on the edge of the target image. Effect. Bilateral filteri...

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 present invention discloses a deep learning-based insulator identification method. The insulator identification method comprises the steps of pre-processing an aerial image, and secondly, extending the data via the methods, such as the geometric transformation, the contrast enhancement, an analog noise adding method, etc.; acquiring the insulator samples, aiming at the insulators of different types, classifying to acquire; determining a to-be-trained model structure; inputting the samples in the to-be-trained model, and continuously adjusting the weights and the bias parameters by the forward propagation and backward propagation methods, and finally determining an optimal model parameter, based on the trained model, taking a to-be-detected image as an input signal, and by the network multi-layer convolution, pooling and full-connection operations, obtaining a final detection identification result. According to the present invention, by a deep learning method, the insulator characteristics are learned continuously, a learning network model is determined, the different insulators are identified under different background environments, and support is provided for the electric power maintenance decisions.

Description

technical field [0001] The invention relates to an insulator recognition method based on deep learning, and belongs to the technical field of insulator recognition of transmission line UAV images. Background technique [0002] Since the transmission line has to withstand the wind, rain, and sun for a long time, coupled with its own mechanical fatigue, the insulator will be broken, cracked and other damage, so that the insulator cannot function normally, which will lead to the danger of the transmission line. Relevant data show that According to statistics, about 80% of the faults of domestic transmission lines are caused by the failure of insulators. The main function of the insulator on the transmission line is to fix the transmission line. Once a fault occurs, it will cause contact between the transmission line and the transmission line or between the transmission line and the tower, resulting in interruption of power supply, and even a large-scale power outage in severe c...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/13G06V10/443G06F18/214
Inventor 杨恒虢韬沈平陈凤翔王伟杨渊时磊刘晓伟李德洋田丁
Owner GUIZHOU POWER GRID CO LTD
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