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

SAR target discrimination method based on non-similarity transformation A-type SVM model

A non-similarity and model technology, applied in the field of SAR target identification and target recognition, can solve problems such as difficulty in model parameter selection

Active Publication Date: 2016-09-28
XIDIAN UNIV +1
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To solve the problem of difficult model parameter selection, and improve the final identification effect when the data distribution is complex

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 target discrimination method based on non-similarity transformation A-type SVM model
  • SAR target discrimination method based on non-similarity transformation A-type SVM model
  • SAR target discrimination method based on non-similarity transformation A-type SVM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] refer to figure 1 , the present invention is based on the SAR target identification method of a class of SVM model of non-similarity transformation, including the following two stages of training and testing.

[0045] 1. Training stage

[0046] Step 1: Use n pieces of SAR training target image set F to obtain a binary image set T of the training target.

[0047] 1a) For n pieces of SAR training target image set F={F 1 ,F 2 ,...,F i ,...,F n} in the i-th training target image F i Perform logarithmic transformation to obtain the logarithmically transformed image G i , and then get the logarithmically transformed image set G={G 1 ,G 2 ,...,G i ,...,G n}, where the logarithmically transformed image G i The amplitude at the pixel point (x, y) is:

[0048] G i (x,y)=10×ln[F i (x,y)+0.001]+30,

[0049] i∈{1,2,...,n}, F i (x,y) is the i-th image F i Amplitude at pixel (x, y), G i (x,y) is the logarithmically transformed image G i Amplitude at pixel (x, y);

...

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 target discrimination method based on non-similarity transformation A-type SVM model. The method includes the steps of 1. preprocessing a training image and a testing image to obtain a training and testing sample set; 2. constructing a non-similarity transformation A-type SVM model based on the training sample set to deduce the combined posteriori distribution of model parameters; 3. deducing the condition posteriori distribution of a single model parameter based on the combined posteriori distribution of the model parameters; 4. sampling the model parameters for I times by means of Gibbs sampling, starting from I+1 and storing the sampling result for one time for every I<sp> interval, and saving for T<s> times; 5. obtaining the testing samples after the characteristic transformation and the corresponding clustering labels based on the stored sampling result; and 6. bringing the transformed testing samples into the A-type SVM corresponding to the clustering labels to output testing object class labels. The method has the advantages of convenient model parameter selection and high identification performance, and is applicable to SAR target discrimination.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing, and in particular relates to a SAR target identification method, which can be used for target identification. Background technique [0002] Synthetic Aperture Radar (SAR), as an imaging radar, can carry out target detection all-weather and all-weather. With the continuous development of SAR imaging technology, SAR image automatic target recognition technology has become a hot research topic at home and abroad. [0003] The Lincoln Laboratory of the United States proposed a three-level processing flow chart for automatic target recognition of SAR images and has been widely used. The process consists of three basic stages: detection, identification, and classification. Discrimination, as an intermediate step in target recognition, plays a decisive role in the final recognition result. Generally, the identification results can be improved from two aspects: (1) extracting features ...

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): G06K9/62
CPCG06F18/23G06F18/2411G06F18/2451
Inventor 杜兰张维李莉玲和华刘宏伟
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