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

An improved hyperspectral end member extraction method based on discrete variables

An endmember extraction and discrete variable technology, applied in the field of hyperspectral images, can solve the problems of easy failure and low accuracy of linear constraint models, and achieve the effects of improved convergence characteristics, fast convergence speed, and high search accuracy

Inactive Publication Date: 2019-05-28
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above problems, the present invention proposes an improved hyperspectral endmember extraction method based on discrete variables, which realizes the optimization of the accuracy of endmember extraction in hyperspectral images, and solves the low precision of traditional endmember extraction methods and the easy failure of linear constraint models The problem

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
  • An improved hyperspectral end member extraction method based on discrete variables
  • An improved hyperspectral end member extraction method based on discrete variables
  • An improved hyperspectral end member extraction method based on discrete variables

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] An improved hyperspectral endmember extraction method based on discrete variables, the flow chart is as follows figure 1 As shown, the specific steps are as follows:

[0064] (1) The objective function is to minimize the root mean square error between the unmixed spectral data and the original spectral data, and an optimization model for endmember extraction is established in combination with constraints;

[0065] (2) Calculate the food source information based on the artificial bee colony algorithm, and select NP food source information as the initial solution input into the genetic algorithm;

[0066] (3) The optimal solution of the endmember extraction optimization model is obtained based on the genetic algorithm.

Embodiment 2

[0068] On the basis of embodiment 1, described step 1) with the minimum root mean square error RMSE between the unmixed spectral data and the original spectral data as the objective function is as follows:

[0069]

[0070]

[0071] in i∈[1,2,…,N], N is the number of pixels in the spectral image, r i is the original spectral image, is the unmixed spectral image, r i (k) represents the image corresponding to the kth band in the original spectral image, Represents the image of the corresponding k-band in the unmixed spectral image, L represents the number of bands of the spectral image, E=[e 1 , e 2 ,...,e p ] is an endmember matrix, S=[s 1 ,s 2 ,...,s P ]∈R N×P is the abundance matrix, and P is the number of endmembers to be extracted;

[0072] The constraints of the optimized model are: ,s ij ≥0, that is, the sum of endmember abundances is 1, and the endmember abundance is not negative; these constraints can be obtained by fully constrained least squares ...

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 improved hyperspectral end member extraction method based on discrete variables, and the method comprises the steps of firstly, taking the minimum root-mean-square error between unmixed spectral data and original spectral data as an objective function, and building an end member extraction optimization model in combination with a constraint condition; calculating the food source information based on an artificial bee colony algorithm, selecting NP pieces of food source information as initial solutions and inputting the initial solutions into a genetic algorithm; andfinally, obtaining an optimal solution of the end member extraction optimization model based on a genetic algorithm. According to the method, the end member extraction precision optimization in the hyperspectral image is realized by applying the discrete artificial bee colony algorithm and the genetic algorithm to the hyperspectral end member extraction, so that the problems that a traditional endmember extraction method is low in precision and a linear constraint model is liable to fail are solved.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral images, and in particular relates to an improved hyperspectral endmember extraction method based on discrete variables. Background technique [0002] Hyperspectral remote sensing realizes the organic fusion of remote sensing data image dimension and spectral dimension information, and has a huge advantage in spectral resolution, which is a milestone in the development of remote sensing. With the maturity of hyperspectral remote sensing technology, its application fields are becoming more and more extensive, and it has penetrated into various fields of the national economy, such as environmental monitoring, resource investigation, engineering construction, etc. Construction played a major role. Hyperspectral remote sensing technology has been widely used in vegetation ecology, atmospheric environment, geology and mineral resources, marine military and other fields. [0003] The hyperspectra...

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): G06N3/00G06N3/12
Inventor 高浩付峥李荣昊
Owner NANJING UNIV OF POSTS & TELECOMM
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