Hyper-spectral image inter-spectrum sorting method based on key channel protection and spectral clustering

A hyperspectral image and channel protection technology, which is applied in character and pattern recognition, instruments, computer parts, etc., to improve the prediction level and improve the lossless compression ratio

Pending Publication Date: 2022-03-01
HARBIN INST OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the current hyperspectral image compression processing flow in the prior art cannot simultaneously meet the requirements of key channels that are important for the application of priority transmission and use the information of key channels to predict and compress the remaining channels. Spectrum sorting method for hyperspectral images based on key channel protection and spectral clustering

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 image inter-spectrum sorting method based on key channel protection and spectral clustering
  • Hyper-spectral image inter-spectrum sorting method based on key channel protection and spectral clustering
  • Hyper-spectral image inter-spectrum sorting method based on key channel protection and spectral clustering

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0060] Specific implementation mode one: refer to figure 1 Specifically illustrate the present embodiment, the hyperspectral image spectrum sorting method based on key channel protection and spectral clustering described in the present embodiment, comprises the following steps:

[0061] Step 1: Obtain the linear correlation matrix R between spectra;

[0062] Step 2: Weight and normalize the linear correlation matrix R between spectra according to the physical segmentation characteristics to obtain the similarity matrix W;

[0063] Step 3: Select the key channel of interest;

[0064] Step 4: According to the similarity matrix W and using the hierarchical clustering method to obtain the channel grouping, then set the threshold, and set the channel in the group whose number of channels in the group is less than the threshold as the specific channel, and then subtract the key channel from all channels Get common channel after combining with special channel;

[0065] Step 5: Acc...

Embodiment

[0109] combine Figure 6 The overall process is described as follows:

[0110] Step 1: Inter-spectral correlation calculation

[0111] Considering that the linear prediction is used in the prediction stage, the Pearson linear correlation coefficient is used to calculate the correlation. The larger the correlation coefficient, the higher the linear correlation.

[0112]

[0113] Among them, f i (x,y) and f j (x, y) is the pixel gray value of the i-th and j-th channels at the spatial position (x, y), μ i and μ j is the average gray value of the i-th and j-th channel images, and the calculation formula is as follows:

[0114]

[0115] The linear correlation between any two channels of the hyperspectral image can be calculated by formula (4), and the correlation coefficient matrix R is formed.

[0116] Step 2: Correlation coefficient matrix weighting

[0117] According to the physical characteristics of the hyperspectrum, the hyperspectral image can be divided into 11...

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 inter-spectrum sorting method based on key channel protection and spectral clustering, and relates to the technical field of image processing. In order to solve the problem that in the prior art, in a hyperspectral image compression processing flow, key channel requirements of priority transmission playing an important role in application and requirements of prediction compression on residual channels by using information of key channels cannot be met at the same time, the transmission of spectral channels is progressive, so that for subsequent prediction compression, the transmission efficiency of the spectral channels is greatly improved. The prediction capability of the predictor is enhanced along with the increase of the number of the transmission channels, and the specific channels are placed at the end of the sequence, so that the predictor with stronger capability can predict the specific channels which are difficult to predict, and the overall prediction level is improved. According to the application, the demand of preferentially transmitting the key channel which plays an important role in the application and the demand of predicting and compressing the remaining channels by using the information of the key channel can be simultaneously met.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a hyperspectral image spectral sorting method based on key channel protection and spectral clustering. Background technique [0002] The Infrared Atmospheric Sounding Interferometer (IASI) is an important instrument for numerical weather prediction (NWP). It uses 8461 channels to measure atmospheric radiation outside the atmosphere, and the spatial resolution of each channel is 60×1530×16bits. The data volume of such an IASI hyperspectral image is about 1.45Gbytes. Hyperspectral infrared detectors such as IASI produce The large amount of data presents many challenges, especially in terms of data storage, computational cost, information redundancy, and information content. In addition, the physical inversion of hyperspectral images involves solving the integral equation of radiative transfer. Such equations usually have nonlinear problems, and small data disturbances wil...

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 & AuthorityApplications(China)
IPC IPC(8): G06V10/762G06V10/74
CPCG06F18/231G06F18/22Y02A40/10
Inventor陈浩卢俊宏
OwnerHARBIN INST OF TECH