hyperspectral image denoising method combining L0 gradient constraint and local low-rank matrix recovery

A hyperspectral image, low-rank matrix technology, applied in the field of hyperspectral image denoising combined with L0 gradient constraint and local low-rank matrix restoration, can solve the problem of unreacted image structure information, ignoring the spatial non-local similarity of hyperspectral images, etc. problem, to achieve the effect of significant denoising effect and high practical value

Pending Publication Date: 2019-04-19
ZHEJIANG UNIV OF TECH
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(3) Based on the tensor decomposition method, the hyperspectral image is considered as a 3D tensor, and the hyperspectral image is processed by tensor decomposition technology

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 image denoising method combining L0 gradient constraint and local low-rank matrix recovery
  • hyperspectral image denoising method combining L0 gradient constraint and local low-rank matrix recovery
  • hyperspectral image denoising method combining L0 gradient constraint and local low-rank matrix recovery

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0043] The present invention will be further described below.

[0044] Reference figure 1 with figure 2 , A combination of L 0 A hyperspectral image denoising method based on gradient constraint and local low-rank matrix restoration, the method includes the following steps:

[0045] Step 1) Obtain hyperspectral image data to be denoised;

[0046] Step 2) Calculate the L of the hyperspectral image to be processed above 0 Gradient, the formula is as follows:

[0047]

[0048] Where y i,j , c Indicates the c-th channel component at the pixel (i,j), with the following convention: if x≠0, F(x):=1, otherwise, F(x):=0, and if i+1> M,|y i+1,j,c -yi ,j,c |:=0;j+1> N,|y i,j+1,c -y i,j,c |: = 0, Calculate the number of pixels with non-zero vertical and horizontal gradients of the image;

[0049] Step 3) Segment the hyperspectral image into m×n×p fixed-size image blocks, and establish a local low-rank constraint model;

[0050] Step 4) Combine L 0 Gradient constraint and local low-rank const...

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

A hyperspectral image denoising method combining L0 gradient constraint and local low-rank matrix recovery comprises the following steps: 1) obtaining hyperspectral image data to be denoised, and defining a hyperspectral image denoising model; The method comprises the steps of (1) obtaining a to-be-processed hyperspectral image, (2) calculating an L0 gradient matrix of the to-be-processed hyperspectral image, (3) establishing a local low-rank constraint-based model, and (4) establishing a denoising model in combination with L0 gradient constraint and local high-rank property of the local high-spectral image, and recovering the three-dimensional noise-free high-spectral image.

Description

technical field [0001] The invention relates to the field of hyperspectral image processing, in particular to a combination of L 0 Gradient Constrained and Local Low Rank Matrix Restoration for Hyperspectral Image Denoising. Background technique [0002] Hyperspectral images are three-dimensional data composed of two-dimensional spatial information and one-dimensional spectral information. and other fields have been widely used. However, in the process of acquisition and transmission of hyperspectral images, they are often polluted by various types of noise, which greatly reduces the reliability of the data, and also has a serious impact on subsequent unmixing, segmentation and target detection. . Therefore, it is of great significance to study the problem of hyperspectral image denoising. [0003] In recent years, a large number of hyperspectral image denoising methods have been proposed. They can be roughly divided into three categories: namely, band-by-band processin...

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): G06T5/00
CPCG06T5/002G06T2207/10036G06T2207/30181
Inventor 郑建炜杨延红陈胜勇
Owner ZHEJIANG UNIV OF TECH
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