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

Low-rank-represented polarization SAR image classification method based on superpixel features

A low-rank representation and classification method technology, applied in the field of image processing, can solve problems such as limited information

Inactive Publication Date: 2014-06-04
XIDIAN UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional single-polarization imaging radars use fixed-polarization antennas to transmit and receive radio frequency signals, which can only measure one component of the scattered wave vector, and the amount of information obtained is limited

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
  • Low-rank-represented polarization SAR image classification method based on superpixel features
  • Low-rank-represented polarization SAR image classification method based on superpixel features
  • Low-rank-represented polarization SAR image classification method based on superpixel features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0090] Embodiment 2, in conjunction with attached Figure 1-11 describe.

[0091] On the basis of embodiment 1, each eigenvalue solution of the superpixel in described step 4 is as follows:

[0092] (a) Calculate the number of pixels contained in each superpixel respectively.

[0093] (b) From the first superpixel to all superpixels, extract the number of pixels contained in each superpixel, and extract the surface scattering energy P according to the positions of these pixels s , volume scattered energy P v , the secondary scattering energy P d , the scattering power entropy H p And co-polarization ratio R and other characteristics.

[0094] (c) Calculate the P of each superpixel according to the following formula s , P v , P d , H p , mean R,

[0095] The expression for finding the average value is: P i = 1 n Σ j = 1 ...

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 low-rank-represented polarization SAR image classification method based on superpixel features. The method mainly improves the marginal classification accuracy of an existing classical algorithm and mainly comprises the steps that (1) Freeman decomposition is conducted on polarization SAR data, surface scattering energy, volume scattering energy and secondary scattering energy are obtained, and a scattering power entropy and a co-polarization ratio are calculated through the surface scattering energy, the volume scattering energy and the secondary scattering energy; (2) superpixel processing is conducted on an RGB composite graph, and a superpixel result graph is obtained; (3) the average value of five features is extracted from each superpixel, a feature matrix of all the superpixels is built, and each row represents the features of each superpixel; (4) low-rank representation is conducted on the feature matrix, and low-rank coefficients are obtained and clustered; (5) wishart adjustment is conducted on the clustered result, and coloring is conducted finally. Compared with other classical methods, the low-rank-represented polarization SAR image classification method based on the superpixel features can better improve classification accuracy and can be used for polarization SAR image classification.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a polarimetric SAR image classification method based on low-rank representation of superpixel features, which can be used to classify polarimetric SAR images. Background technique [0002] Polarimetric Synthetic Aperture Radar (Polarimetric Synthetic Aperture Radar) has become one of the important development directions of synthetic aperture radar at home and abroad. Compared with single-polarization radar images, polarization SAR images can provide more ground object information. Fast and accurate SAR image classification is the prerequisite for various practical applications. Therefore, the research on the classification of polarimetric SAR images is of great significance. [0003] Traditional single-polarization imaging radars use fixed-polarization antennas to transmit and receive radio frequency signals, which can only measure one component of the scattered wave v...

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): G06K9/62
Inventor 钟桦焦李成何念王爽侯彪马晶晶马文萍
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