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

A Hyperspectral Image Classification Method Combining Multiple Feature Information

A hyperspectral image and feature information technology, which is applied in the field of hyperspectral image classification, can solve the problems of the same spectrum and different objects, and the same object has different spectra, and achieve the effects of solving the same object and different spectrum, improving classification accuracy, and high use value

Active Publication Date: 2022-05-20
NANJING NORMAL UNIVERSITY
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a hyperspectral image classification method that combines a variety of feature information, which can solve the problems of the same object with different spectra and the same spectrum with different objects in the hyperspectral image, and can effectively improve the classification accuracy of the hyperspectral image

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 Classification Method Combining Multiple Feature Information
  • A Hyperspectral Image Classification Method Combining Multiple Feature Information
  • A Hyperspectral Image Classification Method Combining Multiple Feature Information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0040] Such as figure 1 As shown, the present invention provides a hyperspectral image classification method combining multiple feature information, comprising the following steps:

[0041] Step 1, extract spectrum, gradient, texture, and shape characteristic data of the hyperspectral image to be classified: use the existing technology to extract various characteristic information of the hyperspectrum, obtain sample data of different feature spaces, and pave the way for step 3. A variety of feature information is correlated and complementary, which provides more effective information for the correct classification of hyperspectral images, and further improves the classification accuracy.

[0042] Step 2, use the watershed segmentation method to segment the hyperspectral image to be classified, and divide it into seve...

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 classification method combining multiple characteristic information, comprising the following steps: step 1, extracting spectrum, gradient, texture, and shape characteristic data of the hyperspectral image to be classified; step 2, using a watershed segmentation algorithm Segment the hyperspectral image to be classified and divide it into several spatial neighbor groups; step 3, use the MFKSADL model to learn the dictionary and sparse coding; step 4, use the coding coefficients to train the SVM classifier to predict the hyperspectral image test set label. This method can solve the problems of the same object with different spectra and same spectrum with different objects in hyperspectral images, and can effectively improve the classification accuracy of hyperspectral images.

Description

technical field [0001] The invention belongs to the field of hyperspectral image processing, in particular to a hyperspectral image classification method combining multiple feature information. Background technique [0002] In hyperspectral remote sensing images, each pixel is represented by hundreds of spectral values, which correspond to different narrow wavelengths from the visible spectrum to the infrared. Detecting and differentiating various ground features offers the possibility. Therefore, hyperspectral image classification has been widely used in many fields, including environmental protection, land use monitoring, urban planning, deep forest fire detection, atmospheric monitoring, military operations, etc. The rich spectral information in hyperspectral images also contains many challenges and problems, such as the classification problem of high-dimensional small samples, and the phenomenon of "same object with different spectrum, same spectrum with different objec...

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): G06V10/764G06V10/26G06K9/62
CPCG06V10/267G06F18/217G06F18/2411Y02A40/10
Inventor 杨明张会敏
Owner NANJING NORMAL UNIVERSITY
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