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

A Machine Learning-Based Method for CME Detection and Tracking

A technology of machine learning and cutting methods, applied in neural learning methods, instruments, computer parts, etc., can solve the problems of large manpower consumption and achieve the effect of cheap calculations

Active Publication Date: 2021-11-26
NANJING UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the sun is close to its maximum activity, the detection and tracking of CMEs will consume a lot of manpower. The above shortcomings of manual CME catalogs have prompted the development of automatic catalogs.

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
  • A Machine Learning-Based Method for CME Detection and Tracking
  • A Machine Learning-Based Method for CME Detection and Tracking
  • A Machine Learning-Based Method for CME Detection and Tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] Each step of the present invention is described below according to an embodiment.

[0083] Step (1), image preprocessing stage. The 1024×1024 resolution input image LASCO C2 is down-sampled and denoised, and the difference image is calculated.

[0084] Step (11), use the lasco_readfits.pro in the solar physics software package (SSW) to read and download the 0.5-level LASCO C2 file, and then use the reduce_level_1.pro in the SSW to process the 1-level data, which includes dark current, stray light, and distortion , vignetting, metering, time and position correction calibration. After processing, the North Pole direction of the sun is consistent with the North Pole direction of the image. All input LASCO C2 images with 1024 × 1024 resolution are first downsampled to 512 × 512 resolution and aligned according to the coordinates of the center of the sun. All downsampled images are then passed through a noise filter to suppress some sharp noise features. A normalized box...

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 method for CME detection and tracking based on machine learning. Based on white light coronagraph images, the detection and tracking of CME (Coronal Mass Ejection) are realized through four stages of preprocessing, classification, detection and tracking. In the preprocessing stage, the image is downsampled and the difference image is calculated. In the classification phase, a supervised image classification method is used to classify a given white-light coronagraph image into categories with and without CME, and then the mid-level features extracted from the trained CNN are used to detect regions of CME. In the detection stage, CME regions are mined using an unsupervised image co-localization method. In the tracking phase, the image is converted into a polar coordinate system, the CMEs at different positions are divided, and some rules are defined to clean and filter the CMEs, and calculate the basic parameters of all detected CMEs.

Description

technical field [0001] The invention belongs to the fields of computer image processing and computer vision, and in particular relates to a method for detecting and tracking CME based on machine learning. Background technique [0002] Space missions to observe coronal mass ejections (CMEs) date back to the 1970s. The coronagraph on the SOHO satellite has made a great contribution to the CME observation, for example, the Large Angle and Spectrometric Coronagraph Experiment (LASCO) can track the CME from 1.1 to about 30Rs. Since the launch of the Solar TErrestrial RElations Observatory (STEREO), CMEs can be observed from two different telescopes COR1 and COR2 in the instrument package of the Solar Terrestrial RElations Observatory (STEREO). With the massive accumulation of coronal image data, the ability to automatically detect, track different features and construct corresponding event catalogs (especially CMEs) becomes more and more important. On the one hand, this can pro...

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 Patents(China)
IPC IPC(8): G06K9/62G06K9/46G06K9/44G06N3/04G06N3/08
CPCG06N3/08G06V10/34G06V10/40G06V10/44G06N3/045G06F18/241G06F18/214
Inventor 张岩封莉王鹏宇袁汉青卢磊甘渊李舒婷黎辉潘云逸
Owner NANJING UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com