Check patentability & draft patents in minutes with Patsnap Eureka AI!

Hyperspectral image dimensionality reduction method capable of combining low-rank expression with image fusion

A hyperspectral image, low-rank representation technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of unsatisfactory classifier training, time-consuming and labor-intensive manual interpretation, and increased data volume. Achieve high use value, reduce data dimensions, and improve the effect of accuracy

Inactive Publication Date: 2017-12-08
NANJING NORMAL UNIVERSITY
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A significant change from multispectral to hyperspectral is the large increase in the amount of data, which not only makes manual interpretation time-consuming and labor-intensive, but also makes classifier training unsatisfactory, that is, "dimensionality disaster"

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 dimensionality reduction method capable of combining low-rank expression with image fusion
  • Hyperspectral image dimensionality reduction method capable of combining low-rank expression with image fusion
  • Hyperspectral image dimensionality reduction method capable of combining low-rank expression with image fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Embodiments of the invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0042] Such as figure 1 As shown, the present invention discloses a hyperspectral image dimensionality reduction method combining low-rank representation and image fusion, including the following steps:

[0043] Step 1, Transform data space: In order to facilitate the comprehensive processing of data, it is necessary to convert the three-dimensional hyperspectral image X into a two-dimensional matrix D of space-spectrum union;

[0044] For any hyperspectral image X∈R m×n×b , where m and n are the number of rows and columns of its spatial structure, respectively, and b is the number of bands. Record the value of each pixel of the hyperspectral image on all bands as a v...

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 dimensionality reduction method capable of combining low-rank expression with image fusion. The method comprises the following steps that: transforming a data space; detecting significance; calculating similarity; fusing similar wavebands; obtaining fusion data; and recovering data image. By use of the method, the waveband number of the hyperspectral image can be effectively reduced, the hyperspectral image dimensionality reduction is realized, meanwhile, a great quantity of redundant information can be removed, the classification efficiency of the hyperspectral image is improved, and therefore, the method has a high use value.

Description

technical field [0001] The invention relates to a hyperspectral image dimensionality reduction method combined with low-rank representation and image fusion, and belongs to the technical field of hyperspectral image dimensionality reduction processing. Background technique [0002] Hyperspectral remote sensing images have been at the forefront of remote sensing image research since the rise of the 1980s. Hyperspectral remote sensing images are combined with imaging technology and spectral technology to obtain data. The acquired data not only has two-dimensional spatial information of ground objects , also includes one-dimensional spectral information. The benefits of higher resolution hyperspectral imagery are obvious, but a potential downside in the data cannot be overlooked. A significant change from multispectral to hyperspectral is the large increase in the amount of data, which not only makes manual interpretation time-consuming and labor-intensive, but also makes clas...

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): G06T3/00
CPCG06T2207/20221G06T3/067
Inventor 杨明俞珍秒吕静
Owner NANJING NORMAL UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com