Unlock instant, AI-driven research and patent intelligence for your innovation.

Polarization SAR Image Classification Method Based on FQPSO and Target Decomposition

A classification method and target decomposition technology, applied in the field of polarimetric synthetic aperture radar image classification, can solve the problems of inaccurate classification results, insufficient utilization of polarization synthetic aperture radar SAR data scattering information, etc., to improve classification accuracy, edge clear effect

Active Publication Date: 2017-10-24
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the Freeman decomposition does not use the eight-component rotation invariance of the polarimetric SAR data, which leads to insufficient utilization of the scattering information of the polarimetric SAR data and makes the classification results inaccurate

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
  • Polarization SAR Image Classification Method Based on FQPSO and Target Decomposition
  • Polarization SAR Image Classification Method Based on FQPSO and Target Decomposition
  • Polarization SAR Image Classification Method Based on FQPSO and Target Decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0048] Refer to attached figure 1 , the concrete steps of the present invention are as follows.

[0049] Step 1. Input polarimetric SAR image data.

[0050] Step 2. Extract scatter features.

[0051] The polarimetric synthetic aperture radar SAR image data is preprocessed by Lee filtering method, and the coherent speckle noise in the polarimetric synthetic aperture radar SAR image data is filtered out to obtain the polarimetric synthetic aperture radar SAR data.

[0052] Using the Claude Cloude decomposition method, the scattering entropy is extracted from each pixel of the polarimetric synthetic aperture radar SAR data. The specific steps of the Claude Cloude decomposition method are as follows:

[0053] In the first step, calculate the three eigenvalues ​​of the coherence matrix of polarimetric SAR SAR data according to the following formu...

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 polarimetric SAR image classification method based on FQPSO and target decomposition. The realization steps are: (1) inputting polarimetric synthetic aperture radar SAR image data; (2) extracting scattering features; (3) initial classification; (4) Initialize the quantum particle swarm; (5) Calculate the membership degree of the pixel; (6) Update the particle position; (7) Determine that the iteration end condition is reached; (8) Final classification; (9) Output the classification result. The present invention adopts the method of optimizing the initial classification, which overcomes the problem of inaccurate classification of the polarimetric SAR image data by directly classifying the initial clustering center of the polarimetric SAR image data in the prior art, and the present invention can make the classified The accuracy of polarimetric SAR image classification is improved, which can be used for target recognition and ground object classification of different targets in polarimetric SAR images.

Description

technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a polarization synthetic aperture radar (Synthetic Aperture Radar, SAR) based on Fuzzy Quantum Particle Swarm Optimization (FQPSO) and target decomposition in the technical field of image processing and remote sensing ) image classification method. The invention can be used to classify the ground objects of different targets in the polarimetric synthetic aperture radar SAR image. Background technique [0002] In recent years, polarimetric synthetic aperture radar (SAR) has become one of the most advanced sensors in the field of remote sensing. So far, the unsupervised classification of feature-based target decomposition in polarimetric SAR SAR image classification is an important branch of polarimetric SAR SAR image classification. Feature-based target decomposition is generally to decompose the polarization measurement data (scattering matrix, covariance...

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
CPCG06F18/2321G06F18/2111G06F18/2415
Inventor 焦李成马文萍文雯马晶晶王爽侯彪杨淑媛刘静
Owner XIDIAN UNIV