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

A hyperspectral image abundance estimation method based on orthogonal basis

A technology for hyperspectral image and abundance estimation, which is applied in image analysis, image data processing, calculation, etc., to shorten the time of hyperspectral image abundance estimation, improve the efficiency of hyperspectral image abundance estimation, and reduce the computational complexity Effect

Active Publication Date: 2019-05-07
HEILONGJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a hyperspectral image abundance estimation method based on an orthogonal basis to solve the problem of computational complexity in existing methods

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 abundance estimation method based on orthogonal basis
  • A hyperspectral image abundance estimation method based on orthogonal basis
  • A hyperspectral image abundance estimation method based on orthogonal basis

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0040] Specific implementation mode one: as Figures 1 to 4As shown, in this embodiment, the implementation of the hyperspectral image abundance estimation method based on orthogonal bases and the comparison with existing methods are described as follows:

[0041] 1. The UCLS algorithm and the OSP algorithm involve matrix inversion operations, and the SV algorithm requires determinant operations. OVP algorithm overcomes the shortage of UCLS algorithm, OSP algorithm and SV algorithm in computational complexity.

[0042] 2. Unconstrained linear unmixing algorithm

[0043] 2.1 Linear mixed models

[0044] The linear spectral mixture model that is currently studied more can be expressed as

[0045] X=SA+N (1)

[0046] Among them, the pixel vector X is L rows, and the end member matrix S=[S 1 ,S 2 ,...,S P ] is L×P dimension, abundance vector A=[a 1 ,a 2 ,...,a P ] T is the P row, T is the matrix transpose operation, and the noise N is the L row.

[0047] 2.2UCLS Algori...

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 abundance estimation method based on an orthogonal basis, and relates to a hyperspectral image processing technology, which is used to solve the problem that an existing method is complex in operation. The algorithm uses the Gram-Schmidt method to calculate the end vector group to obtain the corresponding orthogonal basis set, solves the unmixed equations, and solves the eigenvectors of each orthogonal basis.; And the to-be-unmixed spectrum vector is projected to the feature vector, and the length ratio of the projection vector to the orthogonal basis is calculated to obtain abundance estimation of the end member represented by the orthogonal basis. Through comparative analysis of different algorithms, the algorithm only needs to perform vectorinner product operation, so that the operation complexity is reduced, the abundance estimation time of the hyperspectral image is shortened, and the abundance estimation efficiency of the hyperspectral image is improved. Through simulation data and actual image data experiments, the effectiveness of the algorithm is verified.

Description

technical field [0001] The invention relates to a method for estimating the abundance of a hyperspectral image, and relates to a hyperspectral image processing technology. Background technique [0002] Hyperspectral images contain rich spatial information and spectral information, and hyperspectral image processing technology is used in geography, geology, agriculture, forestry and other fields. The distribution of ground objects is often complex and diverse, and the spatial resolution of the spectral imager is limited, resulting in a large number of mixed pixels containing various types of ground objects in hyperspectral images. Mixed pixel decomposition is an important problem in hyperspectral image processing. Hybrid cell decomposition includes endmember extraction and abundance estimation. [0003] Pixel mixing models mainly include two categories: linear spectral mixing models and nonlinear spectral mixing models. The linear spectral mixture model is the most widely ...

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): G06T7/40
CPCY02A40/10
Inventor 赵岩周真
Owner HEILONGJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
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