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

Method and device for selecting hyperspectral image band based on key band extraction

A hyperspectral image and band selection technology, which is applied in the field of image processing, can solve the problem of low detection accuracy of hyperspectral image anomalies, achieve the effect of reducing the amount of calculation, achieving good results, and improving the efficiency of band selection

Active Publication Date: 2017-05-31
HANGZHOU DIANZI UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a hyperspectral image band selection method and device based on key band extraction, improve the extraction effect of hyperspectral image key bands, effectively determine the optimal number of bands, and improve the existing multiple The efficiency of this band selection method solves the problem of low accuracy of hyperspectral image anomaly detection due to the correlation between bands

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
  • Method and device for selecting hyperspectral image band based on key band extraction
  • Method and device for selecting hyperspectral image band based on key band extraction
  • Method and device for selecting hyperspectral image band based on key band extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Step 1: Use the HFC (Harsanyi-Farrand-Chang) method to determine the number of endmembers.

[0061] (1) Calculate the covariance matrix K of the image data L×L and the autocorrelation matrix R L×L .

[0062] (2) Calculate the eigenvalue sets of the covariance matrix and the autocorrelation matrix respectively, denoted as {λ 1 ≥λ 2 ≥…λ L}and where L is the number of spectral bands.

[0063] (3) Obtain the approximate noise variance value of the lth band of the spectral image Where M×N represents the number of elements in the image.

[0064] (4) Calculate the probability density function

[0065] (5) Given the false alarm probability P F ,according to and get τ l value

[0066] (6) Satisfied The number of eigenvalues ​​of is the number of bands sought.

[0067] Step 2: Use the FNSGA (Fast NewSimplexGrowing Algorithm) simplex growth algorithm to realize endmember extraction and obtain the endmember spectral curve.

[0068] (1) For each pixel r in t...

Embodiment 2

[0105] Steps 1 to 4 of Embodiment 2 are exactly the same as Embodiment 1.

[0106] Step 5: For the data corresponding to the key band subset, use the band selection method based on the maximum amount of information to select the band.

[0107] Suppose there are k bands in the key band set, and the data of k bands is denoted as Φ 2d ={B 1 ,B 2 ,...,B k}∈R MN×k , where MN=M×N. The number of bands required for band selection is set to num(num

[0108] For the C matrix obtained in step 4

[0109] (1) Calculate maxC=max(C), define the set

[0110] (2) Calculate the minimum value of each row element of the C matrix, denoted as minR i , (i=1,2,3,...,k);

[0111] (3) calculation And adjust SET=SET∪g;

[0112] (4) Modify the elements of the C matrix to make C(g, i)=C(g, i)=maxC;

[0113] (5) If the number of elements in SET is less than k-num, skip to step (3), otherwise skip to step (6);

[0114] (6) Remove the elements in SET from the key band subset KeySet, and 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 discloses a method and device for selecting a hyperspectral image band based on key band extraction. The method is specifically implemented by: determining the number of end members of a hyperspectral image, and extracting end member spectrums; extracting a key point subset for each end member spectrum by using a method based on three-point vector included angle and variation amplitude analysis, and combining all the key point subsets to construct a candidate band subset; according to the characteristic that inter-band similarities have clustered distribution, constructing a visibility graph of a local information divergence matrix, and determining a range of an optimum band number; and finally, selecting the best one of an information quantity measuring method and an optimum subset selection criteria method, thereby determining the optimum band subset. Key bands of the end member spectrums provided in the method disclosed by the invention are most distinguishing feature bands among different ground objects, an optimum band is selected from the key band subset, and the time of subsequent band selection can be shortened, so that the band selection method disclosed by the invention can improve the efficiency of band selection.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a hyperspectral image band selection method and device based on key band extraction. Background technique [0002] Hyperspectral remote sensing is a new type of remote sensing detection technology developed in recent years, which has broad application prospects. Hyperspectral remote sensing images generally consist of hundreds of bands and contain rich spatial, radiometric and spectral information. However, a large number of bands increases the time for hyperspectral image anomaly detection, and the correlation between bands reduces the detection accuracy. Therefore, the prerequisite for effective use of hyperspectral data is to select appropriate features to reduce the dimensionality of hyperspectral data. There are two existing methods to achieve dimensionality reduction: one is feature extraction, and the other is band selection. The method of feature extraction will cause th...

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): G06K9/00
CPCG06F2218/10G06F2218/12
Inventor 黄珍赵辽英张文强厉小润
Owner HANGZHOU DIANZI UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com