A non-local weighted joint sparse representation method for hyperspectral image classification

A hyperspectral image and joint sparse technology, applied in the field of hyperspectral image classification, can solve problems such as excessive dimensionality, and achieve the effect of overcoming excessive dimensionality, ideal classification effect, and reducing interference

Active Publication Date: 2019-01-04
SHANTOU UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Can make full use of hyperspectral remote sensing data to solve a series of problems caused by its high dimensionality

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 non-local weighted joint sparse representation method for hyperspectral image classification
  • A non-local weighted joint sparse representation method for hyperspectral image classification
  • A non-local weighted joint sparse representation method for hyperspectral image classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0026] A non-local weighted joint sparse representation hyperspectral image classification method according to an embodiment of the present invention includes the following steps.

[0027] The similarity between pixels is measured by using the spectral angle between pixels instead of the Euclidean distance. The formula for the spectral angle θ is shown in (1), where x n and x m Represents different hyperspectral image pixels, parameter b represents the bth band of the hyperspectral image, and B represents the total number of bands of the hyperspectral image. First, a certain proportion of randomly selected training samples (that is, an over-complete dictionary) is used, and the rest are used as test samples. The samples of training set and test set are as Figu...

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 embodiment of the invention discloses a non-local weighted joint sparse representation hyperspectral image classification method. Firstly, an adaptive threshold value is obtained according to a training sample; then, the threshold and cross-window similarity methods are used to exclude the points with large class differences and calculate the weights of the remaining points; then the joint signal matrix is obtained by weighting the points in the search window with the obtained weights; finally, the joint sparse signal matrix is used for joint sparse representation classification, and the classification of the center points to be measured is obtained. As the spectral angle between pixel is used to replace the Euclidean distance to measure the similarity between pixel, the data information of the hyperspectral remote sensing data is fully utilized, a series of problems caused by the hyperspectral remote sensing data are overcome, the classification effect of the sparse representationis ideal, and the interference of the heterogeneous points to the center point to be measured is well reduced.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to a hyperspectral image classification method based on non-local weighted joint sparse representation of adaptive threshold. Background technique [0002] Since the hyperspectral imaging technology was proposed in the 1980s, its research has never stopped. The current hyperspectral remote sensing data generally has dozens or even hundreds of spectral band information, and the rich spectral information makes it have unique advantages in identifying and distinguishing various types of ground objects. Not only that, with the continuous improvement of the spatial resolution of current hyperspectral sensors, even ground features with small spatial structures can be analyzed through hyperspectral remote sensing images. Due to the characteristics of multi-temporal equalization, rich spectral information, and wide coverage, its application technology has also been continuous...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/2136G06F18/241G06F18/214
Inventor 闫敬文陈宏达袁振国王宏志
Owner SHANTOU UNIV
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