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

A hyperspectral image classification method based on adaptive optimization of spatial features

A technology of hyperspectral images and spatial features, which is applied in the field of hyperspectral image classification with adaptive optimization of spatial features, can solve the problems that morphological filtering cannot be adapted, and the optimization of different data sets is easy to lose, etc. Filtering effect, the effect of good classification performance

Active Publication Date: 2022-03-15
GUANGDONG COMM POLYTECHNIC
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the defects that the current morphological filtering cannot adapt to different data sets and easily lose spatial correlation information, and propose a hyperspectral image classification method for adaptive optimization of spatial features

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 based on adaptive optimization of spatial features
  • A hyperspectral image classification method based on adaptive optimization of spatial features
  • A hyperspectral image classification method based on adaptive optimization of spatial features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Please refer to figure 1 , figure 1 is the flow chart of the algorithm.

[0068] A hyperspectral image classification method for adaptive optimization of spatial features, comprising the following steps:

[0069] S1: Normalize the hyperspectral image to obtain a hyperspectral image dataset R with redistributed information; where min is the minimum value, max is the maximum value;

[0070] The reflection intensity value of the pixel in the hyperspectrum is relatively large, according to the formula The hyperspectral data set with the number of bands L is normalized, min is the minimum value, and max is the maximum value, and the hyperspectral image data set R with redistributed information is obtained.

[0071] S2: Perform PCA dimensionality reduction on the normalized hyperspectral image;

[0072] For the hyperspectral data set R with L bands, PCA dimensionality reduction is performed, and the previous n-dimensional data is selected to form a new data set P, that i...

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 vegetation classification method for spatial feature self-adaptive optimization, comprising the following steps: first performing normalization processing on the hyperspectral image, and then performing PCA dimensionality reduction on the normalized hyperspectral image , then perform morphological filtering on the hyperspectral image after PCA dimensionality reduction to obtain the spatial information set; Perform linear superposition and fusion of spatial information, and finally classify the fused spatial information set. The invention effectively utilizes the spatial texture information and the correlation information, further optimizes filter parameters of the structure type with the best classification, obtains a better filtering effect, and effectively improves the classification accuracy of hyperspectral images.

Description

technical field [0001] The present invention relates to a hyperspectral image classification method, in particular to a hyperspectral image classification method for adaptive optimization of spatial features. Background technique [0002] Hyperspectral imaging technology has high spectral resolution. Hyperspectral remote sensing images obtained by imaging spectrometers can reach spectral information of hundreds of bands, and can obtain more comprehensive and spectral features of ground objects, thereby greatly improving the classification of ground objects. degree and accuracy. Using morphological filtering to extract spatial information and combining space and spectrum to improve the classification performance of hyperspectral images is a research hotspot at present. Some scholars use various morphological feature extraction methods and implement classification by SVM. [0003] Morphological filtering has achieved certain results in the research of hyperspectral image spat...

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): G06V10/44G06V10/764G06K9/62
CPCG06V10/443G06F18/2411
Inventor 廖建尚
Owner GUANGDONG COMM POLYTECHNIC
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