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

High spectral waveband selection method based on entropy redundancy and clonal selection

A technology of band selection and clone selection, which is applied in the field of dimensionality reduction of hyperspectral images, can solve problems such as the inability to accurately calculate the pros and cons of band combinations

Inactive Publication Date: 2017-03-08
HARBIN INST OF TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can solve the problem that it is impossible to accurately calculate the pros and cons of the band combination during the band selection process

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
  • High spectral waveband selection method based on entropy redundancy and clonal selection
  • High spectral waveband selection method based on entropy redundancy and clonal selection
  • High spectral waveband selection method based on entropy redundancy and clonal selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The specific implementation manner of the present invention will be described below in conjunction with the embodiments and accompanying drawings: the hyperspectral band selection method based on Tsallis entropy redundancy and clone selection is applied to hyperspectral image band selection.

[0049] First, a description of the hyperspectral image data is given:

[0050] The experimental object is Indian Pines hyperspectral image data, the wavelength range is 400nm-2500nm, it contains 224 bands, and the size is 145×145pixel. In the data set, several bands of atmospheric absorption interference were eliminated, leaving 220 bands as experimental objects, and the image data was recorded as IMG (145×145,220) .

[0051] In this example choose w The value range of is 5~30, and the bands containing important information are selected from the 220-dimensional bands to reduce the dimensionality, that is, a band combination with a number of 5~30 is selected from a group of 220...

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 a high spectral waveband selection method based on entropy redundancy and clonal selection, belongs to a dimension reduction method of a high spectral image, and solves the problem that a waveband image cannot be evaluated reasonably in the waveband selection process of the high-spectral image. The method comprises the steps that 1) the high spectral image is read in, an initial antibody waveband is generated, an antibody waveband affinity coefficient is calculated by utilizing the Tsallis entropy redundancy, and an optimal antibody waveband is selected according to the affinity coefficient; 2) the optimal antibody waveband is cloned to generate a temporary antibody waveband, a high-frequency variation operation is carried out, and an optimal antibody waveband is selected again; and 3) antibody wavebands of relatively low affinity coefficient are replaced, and iterative computation is carried out, and is not stopped till the specific iteration frequency is reached. The Tsallis entropy redundancy serves as a criterion function for waveband selection, the waveband of the high spectral image can be selected in high efficiency, and the method is suitable for fields including dimension reduction and data compression of the high spectral image.

Description

technical field [0001] The invention relates to a dimensionality reduction method of a hyperspectral image, in particular to a hyperspectral band selection method based on Tsallis entropy redundancy and clone selection. Background technique [0002] Hyperspectral imagery is a mass data source that combines imagery and spectrum. It contains both image information and spectral information. It can provide spectral intensity data of each pixel on each spectral segment and has high spectral resolution. With the development of remote sensing technology and hyperspectral imagers, hyperspectral images are more and more widely used in the military field, mainly in the aspects of UAV search and identification, satellite stability control, anti-stealth detection and map drawing, etc. It has the characteristics of too many bands and too much data, which brings great difficulties to the classification and recognition of hyperspectral images. For example, the information redundancy is hi...

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): G06T7/00
CPCG06T7/0002G06T2207/10036
Inventor 张淼于文博沈毅王艳
Owner HARBIN INST OF TECH
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