Spider web mode and convolutional neural network based star map identification method

A convolutional neural network and star map recognition technology, applied in the field of star map recognition based on spider web mode and convolutional neural network, to achieve the effect of high recognition rate and good robustness

Active Publication Date: 2018-03-20
BEIHANG UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Step 1, for the problem of current pattern recognition class algorithm, the present invention proposes a kind of spider web pattern star map, and its construction process is as follows:

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
  • Spider web mode and convolutional neural network based star map identification method
  • Spider web mode and convolutional neural network based star map identification method
  • Spider web mode and convolutional neural network based star map identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0029] 1. Construct the spider web pattern, as follows:

[0030] a) Determine the main star and the radius of the model, the model of the main star is composed of the companion stars in the neighborhood determined by the model radius.

[0031] b) Translate the main star so that the main star is located in the center of the field of view.

[0032] c) Connect the companion star and the main star with colored line segments in turn, and calculate the angular distance between adjacent companion stars.

[0033] d) In order to increase the degree of differentiation of different main star modes and the information in the star map, the adjacent companion stars are connected with 6 different color line segments according to the size of the angular distance. The colors corresponding to the angular distance are shown in the table below. The main...

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 spider web mode and convolutional neural network based star map identification method. The method comprises the following steps: creating a spider web mode star map in whichthe relative location relation between a main star and companion stars and the angular distance relation of the companion stars are utilized and color information is included; making a training set and a testing set of the spider web mode star map based on a star catalogue; and proposing a convolutional neural network suitable for the spider web mode. According to the method, a high correct identification rate can be obtained under loud noise at star location and star magnitude noise; in addition, a matching star point can be obtained in case of few companion star points within the radius of anavigation star point mode.

Description

technical field [0001] The invention relates to the field of star map recognition, in particular to a star map recognition method based on a spider web pattern and a convolutional neural network. Background technique [0002] It is one of the three key technologies of the star sensor to identify the star point image observed by the star sensor and find out the corresponding position of the image star point in the global star library. Whether the star map recognition is correct or not directly determines whether the star sensor can correctly output the attitude of the spacecraft, and the speed and robustness of the star map recognition also directly determine the real-time and reliability of the output attitude. At present, star map recognition algorithms can be roughly divided into two categories: subgraph isomorphism algorithms and pattern recognition algorithms. [0003] The subgraph isomorphism algorithm regards the star points as the vertices of the graph, and the angul...

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): G01C21/02G01C21/20
CPCG01C21/02G01C21/20
Inventor 江洁刘雷张广军
Owner BEIHANG 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