A Feature Extraction Method of Neighborhood Fitting RCS Sequence

A feature extraction and neighborhood technology, applied in the direction of instruments, complex mathematical operations, calculations, etc., can solve the problem of ignoring the local structural features of target recognition, and achieve the effect of improving target recognition performance

Active Publication Date: 2019-11-19
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional transformation method ignores the local structural features that are more conducive to target recognition, so there is room for further improvement in the recognition performance of the existing traditional transformation method

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
  • A Feature Extraction Method of Neighborhood Fitting RCS Sequence
  • A Feature Extraction Method of Neighborhood Fitting RCS Sequence
  • A Feature Extraction Method of Neighborhood Fitting RCS Sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The actual application effect of the present invention is described below in conjunction with simulation data:

[0034] Design four kinds of dummy targets: real target, debris, light bait and heavy bait. The real target is a conical target, its geometric dimensions: length 1820mm, bottom diameter 540mm; light bait is a conical target, its geometric dimensions: length 1910mm, bottom diameter 620mm; heavy bait is a conical target, its geometric dimensions: length 600mm, Bottom diameter 200mm. The precession frequencies of true target, light bait and heavy bait are 2Hz, 4Hz and 10Hz, respectively. The RCS sequences of true targets, light decoys and heavy decoys are calculated by FEKO, the radar carrier frequency is 3GHz, and the pulse repetition frequency is 20Hz. The RCS sequence of the fragments is assumed to be a Gaussian random variable with a mean of 0 and a variance of -20dB. The polarization mode is VV polarization. The calculation target runtime is 900 seconds....

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 belongs to the technical field of radar target recognition, in particular to a neighborhood fitting RCS sequence feature extraction method. The method of the present invention first uses the neighborhood sample feature to fit a certain sample feature, uses the fitting error as the objective function, establishes the transformation matrix, and uses the feature extracted by the transformation matrix to maintain the local structure information of the sample neighborhood, thereby improving the The target recognition performance overcomes the shortcomings of traditional transformation methods that can only extract global structural features. Simulation experiments are carried out on the RCS data of four types of simulation targets, and the experimental results verify the effectiveness of the method.

Description

technical field [0001] The invention belongs to the technical field of radar target recognition, in particular to a neighborhood fitting RCS sequence feature extraction method. Background technique [0002] In radar target recognition, the traditional transformation method analyzes the data from an overall perspective, and can extract the global structural features of the target data. For example, the principal component analysis transformation method can maintain the main energy direction of the distribution of all training target data, and identify the target category based on the difference characteristics of the main energy direction, while the discriminant vector transformation method increases the difference between the characteristics of heterogeneous targets while reducing the similarity. The difference between target features, thereby improving the target recognition rate. However, the traditional transformation method ignores the local structural features that are...

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): G06K9/46G06F17/16
CPCG06F17/16G06V10/462
Inventor 周代英冯健张瑛
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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