Aurora image detection method based on deep learning two-dimensional principal component analysis network

A two-dimensional principal component, deep learning technology, applied in instrument, character and pattern recognition, scene recognition and other directions, can solve the problem of aurora image feature extraction, affecting the accurate classification of aurora images, etc., to improve the classification accuracy, realize computer automatic The effect of classification

Active Publication Date: 2015-11-25
XIDIAN UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing studies on aurora images are based on the binary classification of arc and non-arc, and have not achieved good results in the three-classification of aurora images. The reason is that the features of aurora images are not fully extracted, so that Affected accurate classification of auroral images

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
  • Aurora image detection method based on deep learning two-dimensional principal component analysis network
  • Aurora image detection method based on deep learning two-dimensional principal component analysis network
  • Aurora image detection method based on deep learning two-dimensional principal component analysis network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The content and effects of the present invention will be further described below in conjunction with the accompanying drawings.

[0025] Step 1: Extract the first-order global feature U of the aurora image.

[0026] The research object of this example is the aurora image, which is the aurora image captured by the all-sky camera of the Yellow River Station in the Arctic of my country at the Yellow River Station. The steps of extracting the first-order global features of the aurora image are as follows:

[0027] 1a) Extract the L of the aurora image 1 a first-order eigenvector

[0028] A variety of existing methods can be used to extract the first-order feature vector of the aurora image, such as two-dimensional principal component analysis, principal component analysis and other methods. In this example, the two-dimensional principal component analysis method is used to extract the L of the aurora image. 1 a first-order eigenvector Proceed as follows:

[0029] 1a...

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 aurora image detection method based on a deep learning two-dimensional principal component analysis network. With the method, a problem of insufficient information extraction of an aurora image in the prior art can be solved. The method comprises the following steps: (1), a first-order feature vector is extracted by using a two-dimensional principal component analysis network and a first-order filter matrix is generated, thereby obtaining a first-order global feature; (2): a second-order feature vector is extracted for the first-order global feature, and a second-order filter matrix is generated to obtain a second-order global feature; (3), blocked histogram statistics is carried out on the second-order global feature and blocked histogram features are extracted; and (4), blocked histogram features are classified by using a support vector machine classifier to obtain a classification result. According to the invention, automatic detection of computers of existing three kinds of aurora images can be realized. The method having an advantage of high classification accuracy can be used for feature extraction of aurora images and computer image detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to an aurora image detection method, and can be used for feature extraction and classification of aurora images. Background technique [0002] Aurora is an atmospheric luminescence phenomenon excited by high-energy particles from the magnetosphere settling into the upper atmosphere and colliding with neutral components. Therefore, people can obtain a large amount of information on the magnetosphere and solar-terrestrial space electromagnetic activities through the systematic observation of the shape of the aurora and its evolution, which is helpful for in-depth research on the influence of solar activities on the earth. significance. As an important form in nature, aurora images reveal geomagnetic activity and pulsation phenomena in the magnetosphere through their distribution and occurrence. The research on the classification of aurora images has reached a level that is diffic...

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): G06K9/00G06K9/62
CPCG06V20/13G06F18/213G06F18/2411
Inventor 韩冰贾中华高新波李洁宋亚婷王平王秀美王颖
Owner XIDIAN 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
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