Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Aerial power component image classification method based on knowledge transfer learning

A technology of transfer learning and classification method, which is applied in the field of classification of aerial photography power component images based on knowledge transfer learning, can solve the problems of huge amount of data, complex background of aerial photography power component images, and indeterminate shooting angles, etc., to improve the ability of expression and classification Good effect, ensure the effect of safe operation

Active Publication Date: 2019-11-19
ZHONGBEI UNIV
View PDF8 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: how to solve the problem that it is difficult to realize accurate classification and precise positioning of power components due to the complex background of the aerial power component image, the uncertain shooting angle, and the huge amount of data

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
  • Aerial power component image classification method based on knowledge transfer learning
  • Aerial power component image classification method based on knowledge transfer learning
  • Aerial power component image classification method based on knowledge transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Aerial photography of power transmission lines by drones is used to inspect the lines. While improving the efficiency of inspections, a large number of images of power components will also be collected. For traditional digital image processing algorithms, the classification and detection effect of different power components is not good for factors such as complex background, many types of power components, complex shooting environment, unfixed shooting angle, and mutual adhesion between different types of power components. , Weak applicability. The invention makes full use of the advantages of the convolutional neural network in deep learning, utilizes the characteristics of transfer learning, and utilizes the successful experience of the classic convolutional neural network to classify the collected images of electric components. First establish a sample library of power component images, then use migration learning to create a GoogLeNet-based convolutional neural netw...

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 relates to the field of combination of deep learning and machine vision in artificial intelligence, in particular to a knowledge transfer learning-based aerial power part image classification method, which comprises the following steps of establishing a convolutional neural network GoogLeNet; adjusting and optimizing the convolutional neural network GoogLeNet, on the basis of the convolutional neural network GoogLeNet, replacing the last three layers of the convolutional neural network GoogLeNet with a full connection layer, a softmax layer and a classification output layer, andcarrying out optimization setting; when the network is trained, obtaining the network parameters by combining multiple simulation experiments and a Bayesian optimization algorithm; performing normalization preprocessing on the acquired electric power part images, inputting the images into the set new deep convolutional neural network obtained in the step 2 for learning, and performing classification according to the types of insulators, hardware fittings, towers and the like; and verifying by performing simulation experiments.

Description

technical field [0001] The invention relates to the field of combining deep learning and machine vision in artificial intelligence, which is applied to the classification and identification of power components in the inspection process of transmission lines in power systems, thereby ensuring the safe operation of transmission lines. Background technique [0002] The transmission line is a vital part of the power grid system. As the backbone line of the power grid system, it plays a decisive role in the reliability, long-term, safe and stable operation of the entire power grid, and the long-term effective operation of the power grid system is directly related to healthy development of the national economy. With the implementation of the transmission network construction project, the number of transmission lines has increased sharply, the workload of line inspections has increased sharply, the geographical environment is complex, and the weather conditions are changing, making...

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): G06K9/00G06K9/62G06N3/04G06Q10/06G06Q50/06
CPCG06Q10/0635G06Q50/06G06V20/13G06N3/045G06F18/24155G06F18/214
Inventor 赵俊梅张利平任一峰李晓余永俊白鑫张灵菲
Owner ZHONGBEI UNIV
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
Eureka Blog
Learn More
PatSnap group products