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

A Nonlinear Unmixing Method for Hyperspectral Image Considering Spectral Variability

A hyperspectral image and variability technology, applied in the field of hyperspectral image nonlinear unmixing, can solve the problems of unmixing result deviation and non-linear scene spectral variability.

Active Publication Date: 2021-08-20
FUDAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above-mentioned algorithms only focus on the nonlinear unmixing problem, and do not take into account the spectral variability existing in nonlinear scenes, which will still cause large deviations in the actual unmixing results

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 Nonlinear Unmixing Method for Hyperspectral Image Considering Spectral Variability
  • A Nonlinear Unmixing Method for Hyperspectral Image Considering Spectral Variability
  • A Nonlinear Unmixing Method for Hyperspectral Image Considering Spectral Variability

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0115] The specific embodiments of the present invention will be described using analog data and actual remote sensing image data, respectively.

[0116] Nonlinear solve algorithm for high-spectral remote sensing images considered by spectral variability is represented by Unsc-sv.

[0117] 1, simulation data experiment

[0118] In this section, the UNSUSC-SV algorithm and the dual target non-negative matrix decomposition algorithm BI-Objective NMF [8], based on abundance constraints, non-negative matrix decomposition, nonlinear solicity algorithm, Assknmf [9], to make a comparison The method of smooth constraints proposed by the present invention is also recorded as UNSU-SV to investigate the role of adding smooth constraints. Using the spectral angular distance of the end dollar, the root error RMSE (S) (Root Mean Square Error), the root error RMSE of the end element matrix (A) n ) And reconstruction error RE (Reconstruction Error) compare mix results:

[0119]

[0120]

[01...

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 belongs to the technical field of remote sensing image processing, in particular to a hyperspectral image nonlinear unmixing method considering spectral variability. The present invention first uses the kernel method to map the original data to a high-dimensional feature space, and considers the spectral variation coefficient in the high-dimensional space to perform linear unmixing; at the same time, according to the spatial continuity of the distribution of ground objects, local smoothing is added to the abundance and variation coefficient Constraints make the two have spatial smoothness. This method can perform effective unsupervised nonlinear spectral unmixing in the presence of spectral variability in two nonlinear mixture models, Hapke and GBM. The invention can overcome the problem of spectral variability existing in different nonlinear mixing scenarios, and improve the accuracy of spectral unmixing, which has important significance in practical applications.

Description

Technical field [0001] The present invention belongs to the technical field of remote sensing image processing, and more particularly to a high spectrum image nonlinear solving method. Background technique [0002] Remote Sensing Technology is the emerging comprehensive technology developed in the 1960s, and is closely related to spatial, electronic optical, computer, geography and other science and technology, and is one of the most powerful technical means to study the Earth's resource environment. High spectroscopy remote sensing is a multi-dimensional information acquisition technique combined with spectra techniques and spectral techniques. Its images typically contain hundreds of bands, with high spectral resolution, which can get rich spectral information while obtaining the space distribution of the ground object. It is widely used in many fields such as military reconnaissance, environmental monitoring and geological exploration [1]. However, due to the lower spatial res...

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): G06T5/00G06T5/50
CPCG06T5/002G06T5/50G06T2207/10036
Inventor 智通祥王斌
Owner FUDAN 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