Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Hyper-spectral end member extraction preprocessing method based on space-spectrum combination

An endmember extraction and hyperspectral technology, which is applied in instrument, character and pattern recognition, scene recognition, etc., can solve the problem of low endmember extraction accuracy of hyperspectral images, and achieve the effect of reasonable principle.

Inactive Publication Date: 2018-05-11
BEIJING INST OF ENVIRONMENTAL FEATURES
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned defects in the prior art, the present invention provides a hyperspectral endmember extraction preprocessing method based on space-spectrum combination, which solves the problem that the accuracy of hyperspectral image endmember extraction is not high when the hyperspectral image has high noise. high problem

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
  • Hyper-spectral end member extraction preprocessing method based on space-spectrum combination
  • Hyper-spectral end member extraction preprocessing method based on space-spectrum combination
  • Hyper-spectral end member extraction preprocessing method based on space-spectrum combination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings and preferred embodiments. However, it should be noted that many of the details listed in the specification are only for readers to have a thorough understanding of one or more aspects of the present invention, and these aspects of the present invention can be implemented even without these specific details.

[0035] A hyperspectral endmember extraction preprocessing method based on space-spectrum combination provided by the present invention, its flow chart is as follows figure 1 As shown, it specifically includes the following steps:

[0036] (1) Multi-dimensional Gaussian filtering is performed on the original hyperspectral image to obtain a series of new hyperspectral images;

[0037] Gaussian filtering is a linear smoothing filter, which is suitable for eliminati...

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 hyper-spectral end member extraction preprocessing method based on space-spectrum combination. The method comprises: step one, carrying out multidimensional Gaussian filtering on an original hyper-spectral image to obtain a series of new hyper-spectral images; step one, carrying out spatial homogeneity calculation on the new hyper-spectral images to obtain a spatial homogeneity index corresponding to each pixel in the new hyper-spectral images; step three, processing the original hyper-spectral image by using an unsupervised clustering method and carrying out pre classification on the image to enable one class to be one cluster; step four, for each cluster, determining sub sets of the pixels based on the homogeneity indexes of the pixels and determining an extremecluster; step five, selecting the clusters, carrying out end member extraction on the pixels in the sub sets and extracting one end member pixel for each cluster to obtain one group of end member abundance graphs; and step six, completing image identification and classification based on the end member abundance graphs.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a hyperspectral end member extraction preprocessing method based on space-spectrum combination. Background technique [0002] The rise of hyperspectral remote sensing is one of the greatest achievements of remote sensing technology in the 1980s. The reflection (emission) spectrum signal of the ground object acquired by the hyperspectral imager is recorded in units of pixels. Due to the limitation of the spatial resolution of the sensor and the complexity of the background situation, the hyperspectral image generally has mixed pixels. If the mixed pixels are used as pure pixels for classification, target detection and recognition and other application research, the results will have large errors. This makes the hyperspectral mixed pixel decomposition problem an important and key link in hyperspectral data processing. What we need to do is to decompose the mixed pixels into pure ...

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): G06K9/00G06K9/40G06K9/46G06K9/62
CPCG06V20/13G06V10/30G06V10/40G06F18/23G06F18/241
Inventor 刘畅
Owner BEIJING INST OF ENVIRONMENTAL FEATURES
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
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