A hyperspectral image endmember extraction method based on quantum particle swarm optimization

A hyperspectral image and quantum particle swarm technology, applied in the field of hyperspectral image endmember extraction based on quantum particle swarm algorithm, can solve the problems of sensitivity to noise and abnormal points, easy to fall into local optimal solution, etc., and achieve fast calculation efficiency Effect

Active Publication Date: 2018-03-02
WUHAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But these methods are sensitive to noise and outliers
Some scholars use intelligent optimization algorithm to extract endmembers, which is robust to noise and

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
  • A hyperspectral image endmember extraction method based on quantum particle swarm optimization
  • A hyperspectral image endmember extraction method based on quantum particle swarm optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0038] please see figure 1 , a kind of hyperspectral image endmember extraction method based on quantum particle swarm algorithm provided by the present invention comprises the following steps:

[0039] Step 1: Estimate the endmember number P of the hyperspectral image;

[0040] Step 2: Use row and column encoding to initialize the particle's position. The position of each particle in the particle swarm is a vector with a dimension of 2*P. The value of the first P dimension represents the row number of each initialized endmember in the image, and the value ...

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 hyper-spectral image end member extraction algorithm based on a quantum-behaved particle swarm algorithm. Particles are encoded through row-column encoding to improve the efficiency of search, and a cooperation mechanism is introduced to update the individual optimal location of particles and the historical optimal location of groups to avoid the problem of 'dimension disaster'. In the aspect of objective function design, a maximum volume objective function and a minimum reconstruction residual error objective function are ingeniously combined to select an optimal end member combination. End member extraction can be implemented at reasonable time cost. The searched optimal end member is robust to noise.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a hyperspectral image mixed pixel decomposition algorithm, in particular to a hyperspectral image endmember extraction method based on a quantum particle swarm algorithm. Background technique [0002] Hyperspectral images have been widely used in various fields due to their high spectral resolution and rich spectral information that can provide fine information for object recognition. However, due to the limitation of the spatial resolution of hyperspectral images, the observed pixel value is usually obtained by mixing the spectra of multiple pure substances. We call these pure substances endmembers, and the pixel obtained by mixing endmembers called mixed cells. Although hyperspectral images are being used more and more with the maturity and cost reduction of hyperspectral imaging technology, there are still some limitations in the interpreta...

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): G06T7/00G06N3/12
CPCG06N3/12G06T2207/10032
Inventor 杜博刘蓉张良培张乐飞
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