Not supervised classification process of artificial immunity in remote sensing images

A technology of unsupervised classification and artificial immunity, applied in the field of unsupervised classification of remote sensing images based on artificial immune system, can solve the problem that AIS has not been applied, and achieve the effect of reducing unsupervised classification time, high execution efficiency, and speeding up convergence speed.

Inactive Publication Date: 2006-12-06
WUHAN UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, in the unsupervised classification of

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
  • Not supervised classification process of artificial immunity in remote sensing images
  • Not supervised classification process of artificial immunity in remote sensing images
  • Not supervised classification process of artificial immunity in remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to facilitate understanding of the present invention, at first the theoretical basis of the present invention is provided:

[0033]One of the important functions of the human immune system is to remove foreign objects by producing antibodies. Foreign objects can be microorganisms (bacteria, viruses, etc.), abnormal blood cells, transplanted organs, etc., which are called antigens. The basic building blocks of the immune system are lymphocytes, or white blood cells. These special cells can be mainly divided into two categories: B cells and T cells. Both types of cells have their own unique ecology and produce many Y-shaped antibodies from their surfaces to kill antigens.

[0034] In order to explain the formation mechanism of antibodies, some scholars first proposed the template theory, and later put forward the side chain theory, but none of them can reasonably explain the formation mechanism of antibodies. The mechanism of antibody formation was not explaine...

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 is a remote sensed image artificial immunity non-monitoring classifying method, characterized in: (1) opening to-be-classified remote sensed image and inputting algorithm parameters; 2) selecting various initial antibody populations and memory antibodies non-monitoring classified and storing them into various antibody arrays and memory antibody arrays; 3) making artificial immunity system training on image antigens until the training of the whole image is finished; 4) judging whether to meet training stop condition: if not, starting the next iteration from the step 3); otherwise ending the artificial immunity non-monitoring classification and outputting classification result. And the method inherits biological attributes of the bio-immunity system, having self-organizing, self-learning, self- recognizing and self-memorizing abilities and high intelligence, and high executing efficiency in practice, applying to non-monitoring classification of multi-spectrum, and high-spectrum remote sensed images and able to effectively improve the accuracy of remote sensed image non-monitoring classification.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, in particular to a non-supervised classification method for remote sensing images based on an artificial immune system. Background technique [0002] The unsupervised classification of remote sensing images means that people do not impose any prior knowledge on the classification process in advance, and only blindly classify them naturally according to the distribution law of the spectral characteristics of remote sensing image features. The result of its classification is only to distinguish different categories, and the attributes of the categories are not determined. The attributes are determined after analyzing the spectral response curves of various types and comparing them with field investigations. The traditional unsupervised classification of remote sensing images mainly uses K-means algorithm or ISODATA algorithm. [0003] The basic idea of ​​the K-means algorit...

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): G06K9/62
Inventor 钟燕飞张良培
Owner WUHAN 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