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

A Hyperspectral Image Mixed Pixel Decomposition Method

A hybrid pixel decomposition and hyperspectral technology, applied in the field of hyperspectral image hybrid pixel decomposition, can solve the problem of low decomposition accuracy of hyperspectral image hybrid pixel decomposition, and achieve the effect of increasing the difference and improving the decomposition accuracy

Active Publication Date: 2020-08-07
UNIV OF SCI & TECH BEIJING
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide a hyperspectral image mixed pixel decomposition method to solve the problem of low resolution of hyperspectral image mixed pixel decomposition existing in the prior art

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 Mixed Pixel Decomposition Method
  • A Hyperspectral Image Mixed Pixel Decomposition Method
  • A Hyperspectral Image Mixed Pixel Decomposition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, the hyperspectral image mixed pixel decomposition method provided by the embodiment of the present invention includes:

[0058] S101, acquiring hyperspectral image data;

[0059] S102, constructing an endmember spectral variation matrix within a class according to the endmember spectral variation;

[0060] S103. Perform weighting processing on the hyperspectral image data by using the constructed intra-class endmember spectral variation matrix;

[0061] S104, introducing abundance sparse constraints and constructing an objective function based on weighted processing results, decomposing the constructed objective function using a hierarchical non-negative matrix factorization strategy to obtain an endmember matrix and an abundance matrix.

[0062] The hyperspectral image mixed pixel decomposition method described in the embodiment of the present invention obtains hyperspectral image data; according to the endmember spectral variation situation,...

Embodiment 2

[0105] In order to better understand the hyperspectral image mixed pixel decomposition method described in the embodiment of the present invention, the specific implementation method is described with laboratory simulation data and actual hyperspectral data, and compared with the classic mixed pixel decomposition algorithm.

[0106]1) Laboratory simulation data

[0107] There are two methods of generating simulation data in the embodiment of the present invention: one is spectral data collected by ground object spectrometers, and the other is calling existing spectral databases.

[0108] In this embodiment, due to the large amount of data collected by the spectral data collected by field experiments, a large amount of variation spectral information can be obtained at different times and at different heights, from which the intra-class endmember spectral variation matrix can be calculated; for the existing spectral library For the files in , the spectrum of the same ground obje...

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 provides a hyperspectral image mixed pixel decomposition method, which can improve the hyperspectral image mixed pixel decomposition precision. The method includes: acquiring hyperspectral image data; constructing an intra-class endmember spectral variation matrix according to endmember spectral variation; using the constructed intraclass endmember spectral variation matrix to perform weighting processing on the hyperspectral image data; introducing rich The objective function was constructed based on the degree sparsity constraints and based on the weighted processing results, and the objective function was decomposed by using the hierarchical non-negative matrix factorization strategy to obtain the endmember matrix and the abundance matrix. The invention relates to the field of hyperspectral remote sensing image data processing.

Description

technical field [0001] The invention relates to the field of hyperspectral remote sensing image data processing, in particular to a hyperspectral image mixed pixel decomposition method. Background technique [0002] Hyperspectral remote sensing has developed by leaps and bounds in recent years. The images not only contain the rich spatial information of panchromatic and color photography, but also have more and finer spectral information than multispectral images, making each pixel in the image Corresponds to a smooth and complete spectral curve. In view of the different properties of the spectral curves of different ground objects, the use of hyperspectral remote sensing technology can fully mine the spectral and morphological characteristics of different substances, which lays the foundation for the fine detection of ground objects. However, due to the influence of the complexity of ground objects and the limitation of spatial resolution, the problem of mixed pixels is in...

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): G06K9/00
CPCG06V20/194G06V20/13
Inventor 蓝金辉邹金霖张胜李建勇
Owner UNIV OF SCI & TECH BEIJING
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