SAR Object Classification Method Based on CNN and SVM Decision Fusion

A target classification and decision fusion technology, applied in the radar field, can solve problems such as unsatisfactory target recognition effect, achieve the effect of improving classification effect and reducing interference

Active Publication Date: 2022-05-13
XIDIAN UNIV +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] When using SVM to classify SAR target images, at some angles, two targets may be relatively similar, making the target recognition effect not ideal near these angles

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 Object Classification Method Based on CNN and SVM Decision Fusion
  • SAR Object Classification Method Based on CNN and SVM Decision Fusion
  • SAR Object Classification Method Based on CNN and SVM Decision Fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] refer to figure 1 , is a flow chart of a decision fusion classification method based on SVM and CNN of the present invention; wherein the decision fusion classification method based on SVM and CNN comprises the following steps:

[0025] Step 1: Data initialization.

[0026] 1.1) What the present invention is aimed at is the target recognition of radar SAR image, and for each SAR image, its target category is known; Determine SAR image, described SAR image comprises λ class target, λ≥2, and each class target corresponds to A label, and then get the label y corresponding to the λ class target tr1 、y tr2 ,...,y trλ , each type of target includes at least one target, and the azimuth and elevation angles of all targets in each type of target are the same.

[0027] For the λ class target, the pitch angle is from σ 1 to σ 2 , interval σ 3 , azimuth from ξ 1 to ξ 2 , interval ξ 3 Under SAR imaging, a total of SAR images, where 0°≤σ 1 ≤90°, 0°≤σ 2 ≤90°, σ 1 ≤σ 2 ...

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 method for classifying SAR targets based on decision fusion of CNN and SVM. The idea is: determine a SAR image, the SAR image includes λ-type targets, and divide the λ-type targets to obtain a training set and a test set; Then standardize and subset the test set to obtain the first test subset testx1, the second test subset testx2 and the third test subset testx3; then obtain the standardized feature matrix traindata of trainx, the standardized feature matrix testdata1 of testx1, testx2 After the standardized feature matrix testdata2 and testx3 of the standardized feature matrix testdata3, the parameter matrix W and the offset vector bb are respectively obtained; the first column vector C1, the second column vector C2 and the third column vector C3 are determined; and the final predicted category column vector is obtained ; calculate v 2 class is recognized as v 1 The class probabilities are postscripted as the result of SAR object classification based on CNN and SVM decision fusion.

Description

technical field [0001] The invention belongs to the technical field of radar, and in particular relates to a SAR target classification method based on CNN and SVM decision fusion, which is applicable to the identification and classification of radar targets. Background technique [0002] Support Vector Machine SVM is a commonly used machine learning classification model, which has a good effect on the classification and recognition of small samples, nonlinear and high-dimensional targets; SVM is a supervised classifier, which learns , to find a hyperplane that completely separates different types of targets, and at the same time maximizes the sum of the distances from the two closest points on both sides of the plane to the plane; if the target is linearly inseparable, it can be added by adding a suitable The kernel function maps the target from the low-dimensional space to the high-dimensional space, and then finds a hyperplane to classify the target correctly; by introduci...

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): G06V20/10G06V10/764G06V10/82G06K9/62G06N3/04
CPCG06N3/045G06F18/2411
Inventor 张磊李青伟刘宏伟
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap