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

Hyperspectral Image Classification Method and System Based on Correlation Entropy Principle

A technology of hyperspectral images and classification methods, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of difficulty in learning effective classification features, high sample complexity, and achieve the effect of small sample complexity

Active Publication Date: 2021-08-03
HUAZHONG NORMAL UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a hyperspectral image classification method based on the principle of correlation entropy, to solve the problem that the prior art is difficult to learn effective classification features in the hyperspectral image classification problem, and the existing The problem of high sample complexity of the method improves the performance of spectral image classification

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 Classification Method and System Based on Correlation Entropy Principle
  • Hyperspectral Image Classification Method and System Based on Correlation Entropy Principle
  • Hyperspectral Image Classification Method and System Based on Correlation Entropy Principle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The technical solutions and effects of the present invention will be described in further detail below with reference to the accompanying drawings.

[0051] refer to figure 1 , the implementation steps of the present invention are as follows:

[0052] 1) Input a hyperspectral image, and normalize the image so that the range is within [0, 1]. Order I tr ={I 1 ,I 2 ,Λ,I N} is a training set consisting of N pixels, where I i ∈ R d (i=1, 2, Λ, N) is the i-th training sample, and they belong to class C; normalize the image, and normalize the data value to [0, 1] by the following steps:

[0053]

[0054] Among them, M x =max(I(:)),M n =min(I(:)) are the maximum and minimum values ​​of pixel values ​​on the input image, respectively, and is the pixel I with coordinates (i,j) ij B bands, is the pixel with coordinates (i, j) on the normalized hyperspectral image B bands.

[0055] 2) Select p% of the pixels from the hyperspectral image as training samples,...

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 present invention provides a hyperspectral image classification method and system based on the principle of correlation entropy. First, the input image is preprocessed so that the element values ​​of all spectral vectors are between 0 and 1; second, a small number of samples are selected as training samples , using the designed hierarchical model that combines the dimensionality reduction method and the principle of correlation entropy to extract the spatial spectral features of the hyperspectral image; then, use the trained hierarchical structure to learn the spatial spectral features of the test samples; finally, the features of the test samples Input to KNN classifier to get class labels. The present invention utilizes the principle of correlation entropy to fully combine the spectral and spatial features of hyperspectral data; using the hierarchical model of the present invention, more abstract spatial spectral features can be obtained; due to the characteristics of LDA, the present invention has less sample complexity, only A small number of training samples is needed to obtain better classification results, so it is more conducive to practical applications.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral image classification method and system, which can be used for meteorological monitoring, environmental monitoring, land utilization, urban planning, and disaster prevention and mitigation. Background technique [0002] With the development of spectral imaging technology, hyperspectral remote sensing technology plays an increasingly important role in the earth observation systems of many countries around the world. Hyperspectral images can provide rich spectral information and have been widely used in geological surveys, resource exploration, environmental monitoring, and precision agriculture. Among many applications, hyperspectral image classification has attracted much attention as a common technique. However, due to the characteristics of hyperspectral images, such as high data dimensionality, few training samples, and large spatial variat...

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): G06K9/62G06K9/66
CPCG06V30/194G06F18/241
Inventor 魏艳涛余书剑姚璜师亚飞赵刚童名文
Owner HUAZHONG NORMAL UNIV
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