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

A Virtual Dimension Estimation Method for Hyperspectral Imagery Based on Ridge Ratio Shrinkage

A hyperspectral image and dimensionality technology, which is applied in the field of hyperspectral image virtual dimension estimation based on ridge ratio shrinkage, can solve the problems of poor estimation accuracy of hyperspectral image virtual dimension and cannot guarantee the consistency of estimation, and achieve large Universality and rationality, strong operability and reproducibility, effects of reducing processing time and storage space

Active Publication Date: 2021-03-23
XI AN JIAOTONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The usual practice now is to use the HFC method. The HFC method is based on eigenvalue analysis and Neyman-Pearson detection theory, which is simple and effective, but the hypothesis testing idea used in it cannot guarantee the consistency of the estimate, and the size of the first type of error needs to be Tried to select, resulting in poor accuracy of hyperspectral image virtual dimension estimation

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 Virtual Dimension Estimation Method for Hyperspectral Imagery Based on Ridge Ratio Shrinkage
  • A Virtual Dimension Estimation Method for Hyperspectral Imagery Based on Ridge Ratio Shrinkage
  • A Virtual Dimension Estimation Method for Hyperspectral Imagery Based on Ridge Ratio Shrinkage

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] The first example uses mock data. The TRR method and the NWTRR method proposed by the present invention are compared with other methods, wherein the NWTRR method uses the TRR method after noise whitening. The noise whitening method is as follows: Do preprocessing. Preprocessing includes demeaning and whitening. By performing a linear transformation on the observed data vector to make its mean zero and variance one, the correlation between observations is removed.

[0081] In the process of generating simulated data, we set the virtual dimension of the image to be 5, the white noise to be Legendre white noise, and the signal-to-noise ratio to take four different values ​​of 20, 40, 60, and 80 to increase the accuracy of the comparison. The results are shown in Table 1 Shown:

[0082] The comparative data of table 1. embodiment 1

[0083]

[0084] From the analysis in Table 1, it can be seen that when the signal-to-noise ratio is 20, the above method performs bas...

Embodiment 2

[0086] In the second example, we apply the method TRR of the present invention and other methods used in Example 1 to four actual images for virtual dimension estimation, and the results are shown in Table 2:

[0087] The comparative data of table 2. embodiment 2

[0088]

[0089] The above four actual images are commonly used hyperspectral datasets. It can be seen from Table 2 that the TRR method of the present invention performs well in all four groups of images, the floating range near the virtual dimension is small, and the real virtual dimension is basically estimated correctly. While other methods, such as ELM, which perform well in simulated datasets, suffer significant errors. The performance of HFC and the denoised improved NWHFC is also unsatisfactory in each set of images. Therefore, in general, other methods have large errors.

[0090] To sum up, in the current popular theory of HFC hypothesis testing, we found that it is inconsistent, biased estimation, and ...

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 virtual dimension estimation method based on ridge ratio shrinkage, which includes: extracting the sample matrix of the hyperspectral image to be processed; calculating the covariance matrix and the correlation matrix of the sample matrix, and calculating the characteristics of the two Values ​​and sorted; according to the eigenvalue sequence, construct a ratio sequence; compare the sequence value in the ratio sequence with the preset constraint value, and obtain the virtual dimension of the hyperspectral image to be processed. The estimation method of the present invention abandons the idea of ​​hypothesis testing and directly adopts the algorithm of constructing ratio sequence for estimation, which can improve the accuracy of hyperspectral image virtual dimension estimation.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral image virtual dimension estimation, in particular to a hyperspectral image virtual dimension estimation method based on ridge ratio shrinkage. Background technique [0002] Spectral images with a spectral resolution in the range of 10nm are called hyperspectral images. Through hyperspectral sensors mounted on different space platforms, that is, imaging spectrometers, in the ultraviolet, visible, near-infrared and mid-infrared regions of the electromagnetic spectrum, the target area is simultaneously imaged in tens to hundreds of continuous and subdivided spectral bands ; While obtaining surface image information, it also obtains its spectral information, truly achieving the combination of spectrum and image. Compared with multispectral remote sensing images, hyperspectral images have not only greatly improved in terms of information richness, but also provide the possibility of more reasona...

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): G06K9/62
CPCG06V10/751
Inventor 朱学虎康越刘军民罗兰王一成
Owner XI AN JIAOTONG UNIV
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