Unlock instant, AI-driven research and patent intelligence for your innovation.

A Hyperspectral Nonlinear Unmixing Method Based on Boundary Projection Optimal Gradient

An optimal gradient, hyperspectral technology, applied in instrumentation, computing, electrical digital data processing, etc., can solve the problems of sensitive initial value, large obstacle to unmixing of hyperspectral images, and large amount of calculation.

Active Publication Date: 2018-03-02
WUHAN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the cost of the Bayesian method is a large amount of calculation. The semi-NMF method is easy to converge to the local extremum and is sensitive to the initial value. GDA is a pixel-by-pixel unmixing method, which prevents us from applying it to large hyperspectral images. Unmixing

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 Nonlinear Unmixing Method Based on Boundary Projection Optimal Gradient
  • A Hyperspectral Nonlinear Unmixing Method Based on Boundary Projection Optimal Gradient
  • A Hyperspectral Nonlinear Unmixing Method Based on Boundary Projection Optimal Gradient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0045] Refer to attached figure 1 , the present invention mainly consists of two steps: establishing a mathematical model for hyperspectral image unmixing, and solving a nonlinear unmixing model based on GBM. The real data selected in the embodiment is the Moffett Field hyperspectral data set, which has been used for unmixing based on GBM before. We selected a 50×50 image to verify the experimental effect. After removing the water vapor absorption band, there are 203 bands left. It mainly Contains three endmembers: vegetation, water, and soil. In order to verify the effectiveness of the proposed method, we adopt the following indicators: reconstruction error (RE) and mean spectral angular distance (SMAD), which are defined as follows:

[0046]

[0047]

[0048] where y i and y i represent reconstructed pixels and reference pixels respectively,...

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 hyperspectral nonlinear demixing method based on a boundary projection optimal gradient. According to the hyperspectral nonlinear demixing method, by selecting a special search point, step length is determined by a Lipschitz constant, the optimal convergence rate under boundary constraint is greatly accelerated, and the optimal convergence rate as shown in the specification is achieved. In addition, the boundary projection optimal gradient method can be effectively applied to GBM-based hyperspectral nonlinear demixing, and has the advantages of high convergence rate and no selection sensitivity on initial values.

Description

technical field [0001] The invention relates to the field of hyperspectral image unmixing, in particular to a hyperspectral nonlinear unmixing method based on the optimal gradient of boundary projection. Background technique [0002] Over the past few decades, hyperspectral imaging has been a hot research area for remote sensing applications, such as object detection, spectral unmixing, and object matching and classification. Due to reasons such as hyperspectral imaging sensors and surface changes, mixed pixels widely exist in hyperspectral imaging. In this case, hyperspectral unmixing is necessary for the subsequent quantitative analysis of hyperspectral data. Spectral unmixing involves decomposing the mixed pixels into a series of pure spectral features, called endmembers, and the pure endmembers in each pixel. The proportion of yuan is called abundance. The mixture model for spectral unmixing can be linear or nonlinear, depending on the hyperspectral image to be studied...

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 Patents(China)
IPC IPC(8): G06F19/00
Inventor 梅晓光马泳黄珺马佳义樊凡
Owner WUHAN UNIV