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

Polarized SAR image classification method based on Dirichlet mrf mixture model

A hybrid model and classification method technology, applied in the field of image processing, can solve the problem of inapplicability of polarimetric SAR data, and achieve the effect of maintaining edge information, enhancing data correlation, and good classification results

Active Publication Date: 2019-06-18
XIDIAN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that this type of model introduces spatial structure information through the Euclidean distance of the SAR image feature vector, which is not applicable to polarimetric SAR data

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
  • Polarized SAR image classification method based on Dirichlet mrf mixture model
  • Polarized SAR image classification method based on Dirichlet mrf mixture model
  • Polarized SAR image classification method based on Dirichlet mrf mixture model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with the drawings.

[0039] Reference figure 1 The specific implementation steps of the present invention are as follows:

[0040] Step 1. Input the polarized SAR image.

[0041] The present invention selects the following two polarized SAR images:

[0042] Polarimetric SAR image of Flevoland area: image size is 320×326 pixels; equivalent number of sight is 4; resolution is 2.5652m×2m; radar system is AIRSAR;

[0043] Polarimetric SAR image in Oberpfaffenhofen area: image size is 500×450 pixels; equivalent number of sights is 2; resolution is 3m×0.89m; radar system is ESAR.

[0044] Step 2: Extract and normalize the polarization scattering feature, and establish a normalized polarization scattering feature space F 1 .

[0045] 2a) Extract N polarization scattering features F from the polarization SAR image r , R=1,2,...,N, N=17 represents the number of polarization scattering features. The N polarization scatteri...

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 polarization SAR image classification method based on a Dirichlet MRF mixed model, which mainly solves the problem that the prior art cannot automatically determine the number of categories in the polarization SAR image. The scheme is: 1. Extract and normalize the N polarization scattering features of the polarimetric SAR image, and establish a normalized polarization scattering feature space; 2. Reduce the normalized polarization scattering feature space point by point. 3. Initialize the MRF model using the polarimetric scattering feature space; 4. Estimate the prior parameters and likelihood parameters of the polarimetric SAR image according to the initialized MRF model; 5. Estimate the new label field until the maximum number of iterations is reached and a new label field is determined as the classification result of the polarimetric SAR image. The invention improves classification accuracy and smoothness of homogeneous region classification, better maintains edge information, and can be used for target detection and recognition of polarimetric SAR images.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and particularly relates to a classification method of polarized SAR images, which can be used for target detection and recognition of polarized SAR images. Background technique [0002] Polarized synthetic aperture radar SAR is a high-resolution imaging radar. Its widespread use in the civil and military fields requires polarization SAR image interpretation technology as support, and polarization SAR image classification is an important technology in the field of machine learning and data mining, and it is also one of the important contents of image interpretation. It can provide the overall structure information of the polarized SAR image and reveal the essence of the polarized SAR image. In recent years, the polarization SAR image classification method has always been a hot topic in the frontier research in this field. Among them, the random field model is considered to be a powerful tool...

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
CPCG06F18/22G06F18/2415G06F18/254
Inventor 李明宋婉莹张鹏吴艳
Owner XIDIAN 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