Cuckoo search hyperspectral unmixing method based on nonnegative independent component analysis

An independent component analysis, cuckoo search technology, applied in the field of hyperspectral image preprocessing, can solve the problems of complex distribution, unsupervised automatic extraction of end members, etc., to reduce the parameter dimension, good accuracy, reduce calculation amount of effect

Inactive Publication Date: 2016-05-04
TIANJIN UNIV OF COMMERCE
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The distribution of actual ground objects is often very complicated, which makes the unsupervised automatic extraction of endmembers a difficult point in current research.

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
  • Cuckoo search hyperspectral unmixing method based on nonnegative independent component analysis
  • Cuckoo search hyperspectral unmixing method based on nonnegative independent component analysis
  • Cuckoo search hyperspectral unmixing method based on nonnegative independent component analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Combine below Attached picture The present invention will be further described.

[0038] constrained nonnegative independent Component analysis method

[0039] independent The component analysis method is an unsupervised blind source separation method, and its goal is to give only the observed data X, according to independent property measure, the sources are separated by finding a linear transformation, namely

[0040] Y=WX=US (4)

[0041] In the formula, Y=[y 1 ,y 2 ,L,y L ] T R L×N is the estimate of the source S, and W is obtained by maximizing the Y component independent The obtained orthogonal separation matrix. usually, independent The property measure uses kurtosis, negative entropy and mutual information.

[0042] Non-negative independent Compositional analysis methods will traditional independent Component analysis method pair independent Requirements for separation combined with non-negativity of the source, so that the separation result is a...

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 hyperspectral image unmixing method with combination of a nonnegative independent component analysis method and a cuckoo search optimization method. The hyperspectral image unmixing method concretely comprises the following steps that 1. whitening preprocessing is performed on observation data, second-order correlation is removed, and hyperspectral image unmixing is performed; 2. bound terms of which the abundance summation is one are introduced to construct a target function on the basis of the nonnegative independent component analysis method; 3. an unmixing matrix is calculated by utilizing an optimal parameter value obtained in the step 2, and an abundance matrix is estimated; and 4. endmember spectra is estimated by utilizing a nonnegative least square method. The experimental result of simulation data and real hyperspectral data indicates that the limitation of a conventional independent component analysis method in solving the problem of hyperspectral unmixing can be effectively overcome so that great precision can be obtained.

Description

technical field [0001] The invention relates to the field of hyperspectral image preprocessing means, more specifically, relates to an unsupervised hyperspectral image unmixing method combining a non-negative independent component analysis method and a cuckoo search optimization method. Background technique [0002] As a preprocessing method of hyperspectral images, spectral unmixing is not only an important prerequisite for the accurate classification and identification of ground objects, but also an important condition for the further development of remote sensing technology to quantification. It has important practical significance in terms of efficiency and national defense construction. Hyperspectral images are images that contain spatial and spectral information captured by hyperspectral remote sensing imagers, which can help researchers better extract ground object information. Although the spectral resolution of hyperspectral images is very high, due to the complexi...

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): G06K9/62
CPCG06F18/2323G06F18/23
Inventor 陈雷孙彦慧张立毅李锵刘静光
Owner TIANJIN UNIV OF COMMERCE
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