Spatial information adaptive fusion-based hyperspectral image classification method

A technology of hyperspectral image and spatial information, applied in the field of hyperspectral image classification of adaptive fusion of spatial information, can solve the problem that spatial texture information is difficult to obtain spatial information, insufficient spatial information is obtained, and pixel spatial correlation information is easily lost. problem, to achieve the effect of good spatial correlation and removal of salt and pepper phenomenon

Active Publication Date: 2018-08-14
GUANGDONG COMM POLYTECHNIC
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 1) Insufficient spatial information is obtained during hyperspectral classification;
[0007] 2) It is difficult to obtain complete spatial informa

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
  • Spatial information adaptive fusion-based hyperspectral image classification method
  • Spatial information adaptive fusion-based hyperspectral image classification method
  • Spatial information adaptive fusion-based hyperspectral image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, a hyperspectral image classification method for adaptive fusion of spatial information, including the following steps:

[0049] S1: Normalize the hyperspectral data set with the number of bands l, and obtain the hyperspectral image data set R with redistributed information;

[0050] S2: For the hyperspectral data set R with l bands, perform dimensionality reduction, select a band image for every n bands on average, and extract k D Band images form a new data set D, and the remaining k E Bands form the data set E;

[0051] S3: Use bilateral filtering to k D A band data set D is filtered by bilateral filtering to obtain edge spatial information D bs :

[0052]

[0053] S4: Transform the standard convolution filter pair k with domain conversion E A band data set E is converted into a standard convolution filter to obtain spatial information E ts :

[0054]

[0055] S5: put D bs and E ts Synthesize to get W:

[0056] W=D bs +E t...

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 provides a spatial information adaptive fusion-based hyperspectral image classification method. According to the method, spectral information is extracted as spatial information by usingtwo filters and is classified, so that spatial texture information and correlation information are effectively utilized; through domain transformation standard convolution filtering, a certain spatial texture information can be extracted, and relatively good spatial correlation is kept, so that the deficiency that only the spatial texture information can be extracted through bilateral filtering is made up for; and after adaptive fusion of the spatial texture information extracted through the bilateral filtering and the domain transformation standard convolution filtering, optimal classification performance is obtained through SVM classification, and a non-uniform phenomenon is effectively eliminated, so that the method is especially suitable for hyperspectrum with relatively numerous ground objects and complex distribution.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to a hyperspectral image classification method for adaptive fusion of spatial information. Background technique [0002] Space-spectrum combination to improve the classification performance of hyperspectral images is a research hotspot at present, and the spatial information extraction methods mainly include: 1) Morphological filter feature extraction, 2) Markov random field feature extraction, 3) Image segmentation feature extraction, among which It has become a research hotspot that filters extract image texture information to assist spectral information for effective classification. [0003] Some scholars use Gabor filter to extract texture information to assist hyperspectral classification. Among them, multi-dimensional Gabor filter is used to extract image texture information from multiple angles, and the classification accuracy is improved; Gabor filter is also used to ...

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): G06K9/00G06K9/62
CPCG06V20/194G06V20/188G06F18/2411G06F18/253
Inventor 廖建尚王立国曹成涛
Owner GUANGDONG COMM POLYTECHNIC
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