Hyperspectral image unmixing method

A technology of hyperspectral image and spectral mixing model, which is applied in the direction of complex mathematical operations, etc., can solve the problems of considering the separability of material endmembers between classes and not considering the similarity of material endmembers within a class, so as to improve the unmixing effect, Effect of Improving Unmixing Accuracy

Inactive Publication Date: 2018-09-07
UNIV OF SCI & TECH BEIJING
View PDF3 Cites 9 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 unmixing method to solve the non-negative matrix factorization algorithm in the prior art that only considers the separability of material endmembers between classes, and does not consider the endmember similarity of materials within a class. sexual problems

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
  • Hyperspectral image unmixing method
  • Hyperspectral image unmixing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044]In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.

[0045] The present invention provides a hyperspectral image unmixing method aiming at the problem that the existing non-negative matrix decomposition algorithm only considers the separability of material endmembers between classes and does not consider the endmember similarity of materials within a class.

[0046] Such as figure 1 As shown, the hyperspectral image unmixing method provided by the embodiment of the present invention includes:

[0047] S101, establishing a linear spectral mixture model including in-class and non-intra-class endmembers;

[0048] S102, using the covariance sum of squares between spectra as a correlation function, increasing correlation constraints between endmember spectra within a class, between endmember spectra without a c...

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 unmixing method, which can improve the unmixing precision of end members with similar spectral characteristics. The method comprises the steps of buildinga linear spectral mixing model comprising intra-class and non-intra-class end members; taking a square sum of a covariance among spectra as a correlation function, and adding correlation constraints between the intra-class end member spectra, between the non-intra-class end member spectra and between the intra-class and non-intra-class end member spectra; and according to the built linear spectralmixing model and the determined correlation constraints, establishing a target function, and performing unmixing by applying a non negative matrix decomposition algorithm. The method relates to the technical field of remote sensing image processing.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a hyperspectral image unmixing method. Background technique [0002] Hyperspectral remote sensing is a new imaging technology developed in the field of remote sensing in the early 1980s. A lot of image information data with continuous spectral distribution and small spectral range are obtained. Compared with traditional panchromatic images and multi-spectral remote sensing images, hyperspectral images mainly have the following advantages: the map is integrated, that is, the spectral and image information of ground objects are recorded at the same time; each band is imaged separately, and hyperspectral images are the data of each band Data cubes superimposed together; there are many bands and narrow width, which can provide dozens, hundreds or even thousands of bands for each pixel; the spectral resolution is high, up to 5-10nm; the bands are continuous, a...

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): G06F17/15G06F17/16
CPCG06F17/15G06F17/16
Inventor 蓝金辉张胜邹金霖王陆旸
Owner UNIV OF SCI & TECH BEIJING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap