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

SAR image speckle reduction method based on anisotropy and dictionary learning

An anisotropic and dictionary learning technology, applied in the field of remote sensing image processing, can solve the problems of poor denoising ability and edge protection ability, and achieve the effect of improving the ability and edge protection ability and reducing errors

Pending Publication Date: 2021-04-27
HANGZHOU DIANZI UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing image speckle reduction methods have poor denoising ability and edge protection ability

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
  • SAR image speckle reduction method based on anisotropy and dictionary learning
  • SAR image speckle reduction method based on anisotropy and dictionary learning
  • SAR image speckle reduction method based on anisotropy and dictionary learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] Example: such as Figure 1 to Figure 5 As shown, a SAR image speckle reduction method based on anisotropy and dictionary learning includes the following steps:

[0030] Step 1. Preliminary filtering of SAR image anisotropy:

[0031] First, the gradient values ​​of the image in four directions are calculated by the following formula (1), and the obtained gradient values ​​are substituted into the diffusion coefficient formula (2), and then the threshold is set to generate binary images in four directions, and then added to form A new matrix ranging from 0 to 4, set the value greater than 1 to 1, and set it to 0, and perform morphological processing to obtain the preliminary filter area, I represents the original image, x and y represent the row and column of the pixel, K represents The conduction coefficient controls the sensitivity to the edge of the image, selects the anisotropic filtering area, and obtains the largest connected area by threshold setting and morpholog...

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 an SAR image speckle reduction method based on anisotropy and dictionary learning. An image is filtered through anisotropic diffusion filtering so that the speckle noise in a weak scattering region is reduced, useful information and noise are divided preliminary, then the gradient of the image in the east, south, west and north directions is calculated, a binary image is obtained through a diffusion coefficient and a set threshold value, then a connected region is obtained and a small-area region is removed through morphology, then anisotropic diffusion filtering is carried out on an image in the range, and finally deep denoising is carried out through a prior dictionary learning algorithm.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a SAR image speckle reduction method based on anisotropy and dictionary learning. Background technique [0002] Because of its all-day and all-weather characteristics, synthetic aperture radar (SAR) has important applications in the fields of national defense security, resource survey and geographic mapping. Due to its own imaging characteristics, the image generated by SAR will have coherent speckle noise, which will affect the subsequent analysis and application of the image. This noise is a strong multiplicative noise, which is caused by the coherent accumulation of echoes from scattered points, and is visually displayed as small spots that flicker on and off. How to effectively remove noise and retain useful information to the greatest extent is the key to SAR image processing, and it is also the first step in the application of SAR images. [0003] ...

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 Applications(China)
IPC IPC(8): G06T5/00G06T5/20G06K9/62
CPCG06T5/20G06T2207/10044G06T2207/20024G06F18/28G06F18/214G06T5/70
Inventor 逄博李文涛徐欣韦博
Owner HANGZHOU DIANZI 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