Hyperspectral dimensionality reduction method based on spectral-spatial information maintenance

A hyperspectral and spatial spectrum technology, applied in the field of image processing, can solve the problems of poor discrimination, achieve the effect of improving accuracy, overcoming the large amount of calculation, and improving the recognition rate of ground objects

Inactive Publication Date: 2017-09-26
XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention proposes a hyperspectral dimensionality reduction method based on spatial spectrum information preservation, which mainly aims at t

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 dimensionality reduction method based on spectral-spatial information maintenance
  • Hyperspectral dimensionality reduction method based on spectral-spatial information maintenance
  • Hyperspectral dimensionality reduction method based on spectral-spatial information maintenance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The hyperspectral dimensionality reduction method based on spatial spectral information preservation mainly includes the following steps:

[0037] (1) Band selection for the original hyperspectral data

[0038] The original hyperspectral bands are combined in different ways to generate multiple candidate subsets. Assume that the original hyperspectral image always has l bands H=[h 1 ,h 2 ,...,h l ], select k bands with the greatest difference from these l bands to form the optimal subset. Band selection requires that the selected band subsets have the least redundancy and the largest difference between each band, so that the information of the original band can be preserved to the greatest extent while removing the redundancy.

[0039] (2) Build multiple spatial spectrogram models on selected band subsets

[0040] On a selected subset of bands, a band-by-band similarity relationship between samples is established. According to the neighborhood information of sampl...

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 discloses a hyperspectral dimensionality reduction method based on spectral-spatial information maintenance.<{EN3}>The method introduces waveband selection into the hyperspectral dimension reduction and employs the waveband selection to select a waveband subset having the maximum difference; and the method fully utilizes the spectral-spatial similarity between samples on the selected waveband subset so as to improve the ground object recognition rate, and can be used for fields such as remote sensing ground object ground object observation, military reconnaissance and criminology assistance, etc. The method introduces waveband selection into the hyperspectral dimension reduction and employs the waveband selection to select a waveband subset having the maximum difference; and the method fully utilizes the spectral-spatial similarity between samples on the selected waveband subset so as to improve the ground object recognition rate, and can be used for fields such as remote sensing ground object ground object observation, military reconnaissance and criminology assistance, etc.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a hyperspectral dimension reduction method. Background technique [0002] With the development of remote sensing technology and imaging spectrometers, the application of hyperspectral remote sensing images is becoming more and more extensive. However, it has the characteristics of large number of bands and huge amount of data, which brings great difficulties to the classification and recognition of hyperspectral images, such as high information redundancy, large space required for data storage, long processing time, and due to hyperspectral The image has a large number of bands, which is prone to the curse of dimensionality, that is, the classification accuracy decreases. Therefore, in the case of ensuring the classification and recognition rate of ground objects, it is very necessary to reduce the amount of data and save resources. Hyperspectral dimensionality reducti...

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): G06K9/62G06K9/46
CPCG06V10/48G06V10/58G06F18/213G06F18/214
Inventor 袁媛郑向涛卢孝强
Owner XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
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