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

Hyperspectral Image Unmixing Method Based on Convolutional Neural Network

A convolutional neural network and hyperspectral image technology, applied in the field of hyperspectral image unmixing based on convolutional neural network, can solve the problems of low unmixing accuracy, unfavorable information analysis, etc. high effect

Active Publication Date: 2020-06-23
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a convolutional neural network-based high Spectral Image Unmixing Method

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
  • Hyperspectral Image Unmixing Method Based on Convolutional Neural Network
  • Hyperspectral Image Unmixing Method Based on Convolutional Neural Network
  • Hyperspectral Image Unmixing Method Based on Convolutional Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0025] refer to figure 1 , the specific steps of the present invention are further described in detail.

[0026] Step 1, get the data matrix.

[0027] Use the imaging spectrometer to image the target area, obtain all the bands including the hyperspectral image pixels and the hyperspectral image of the real surface object abundance value corresponding to the pixel, and store the image as a data matrix.

[0028] Step 2, preprocessing the data matrix.

[0029] Use ENVI software to perform atmospheric correction on the data matrix, remove the damaged band data affected by the atmosphere and water vapor in the data matrix, and obtain the corrected data matrix.

[0030] The corrected data matrix is ​​divided into training set and test set according to the ratio of 1:3.

[0031] Step 3, construct a convolutional neural network with a 10-layer structure containin...

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 de-mixing method based on a convolutional neural network. The problems mainly solved are low hyper-spectral image de-mixing accuracy, complex model, longtime consumed and low efficiency in hyper-spectral de-mixing in the prior art. The method includes the following steps: acquiring a data matrix; preprocessing the data matrix; constructing a 10-layerconvolutional neural network containing a pixel-based fuzzy classification structure; training the convolutional neural network; carrying out fuzzy classification; and normalizing the output result of the convolutional neural network to get a de-mixing result. The method introduces a convolutional neural network model containing a pixel-based fuzzy classification structure, and has the advantagesof high de-mixing accuracy, simple model, less computation and easy implementation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a hyperspectral image unmixing method based on a convolutional neural network in the technical field of unmixing. The invention is used for hyperspectral image unmixing processing of various digital devices, and can effectively improve the precision of hyperspectral image unmixing. Background technique [0002] Hyperspectral remote sensing data has the problem of high spectral resolution but low spatial resolution. When substances with different spectra appear in the same pixel, the pixel in this situation is called a mixed pixel. Hyperspectral image unmixing is the process of decomposing the ground object spectral signal (end member) and its spatial distribution (abundance) from the mixed pixels. [0003] Giorgio A.Licciardi and Fabio Del Frate proposed a kind of Unmixing methods based on autoassociative neural networks (AANNs). This method uses the auto-associ...

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): G06T7/00
CPCG06T7/0002G06T2207/10036G06T2207/20081G06T2207/20084
Inventor 张向荣焦李成孙雨佳冯婕安金梁李阳阳侯彪马文萍
Owner XIDIAN UNIV
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