A Micro-Doppler Texture Feature Extraction Method for Aircraft Targets

A Doppler texture and feature extraction technology, which is applied in the field of narrow-band system radar and aircraft target micro-Doppler texture feature extraction, can solve the problems of large amount of calculation and difficult real-time implementation, and achieve improved recognition rate and good generalization effect of ability

Active Publication Date: 2018-10-09
CNGC INST NO 206 OF CHINA ARMS IND GRP
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has better performance, but there is a covariance matrix decomposition, the amount of calculation is too large, and it is difficult to implement in real time in engineering

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 Micro-Doppler Texture Feature Extraction Method for Aircraft Targets
  • A Micro-Doppler Texture Feature Extraction Method for Aircraft Targets
  • A Micro-Doppler Texture Feature Extraction Method for Aircraft Targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0038] The technical idea of ​​realizing the present invention is: firstly carry out ground clutter and fuselage component suppression and spectrum shift to the time-domain echo of the distance unit where a single CPI (Coherent Processing Interval) target is located, so that the fuselage component is located in the zero filter Channel; Next, the one-dimensional LBP value calculation, histogram statistics and normalization are performed on the spectrum of the CPI, and finally the normalized histogram representing the texture feature is obtained for subsequent processing.

[0039] The present invention realizes steps as follows:

[0040] 1) Pretreatment

[0041] In order to maintain the frequency domain characteristics of the target echo as completely as possible, the CLEAN algorithm is used to suppress the ground clutter and the fuselage component and shift the f...

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 relates to a micro-doppler texture feature extraction method of airplane targets. Effective classification and identification of three types of classic airplane targets can be achieved. The method comprises steps of firstly acquiring a micro-doppler spectrum through clutter suppression, fuselage component suppression and frequency spectrum shifting; and then extracting an LBP value and a normalization histogram thereof, which are used for displaying texture features of the micro-doppler spectrum. According to the invention, by extracting texture features which are not sensitive to postures, the method has better generalization ability, the calculating quantity is proper and engineering application is facilitated.

Description

technical field [0001] The invention belongs to the field of signal processing, and specifically relates to a method for extracting micro-Doppler texture features of an aircraft target. The method extracts the LBP (Local Binary Pattern, local binary pattern) histogram of the target micro-Doppler after a series of preprocessing Texture features can effectively classify and identify three typical aircraft targets: helicopters, propellers and jets, and are suitable for narrow-band system radars. Background technique [0002] With the development of radar technology, the basic functions of radar have developed from the initial target detection and position parameter estimation to the stage of radar target classification and recognition, among which narrowband radar target classification and recognition is an important branch of modern radar target classification and recognition, and the typical three There is an urgent need for aircraft-like target classification and recognition...

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): G01S7/41
CPCG01S7/41
Inventor 罗丁利杨磊陈尹翔王勇王亚军徐丹蕾
Owner CNGC INST NO 206 OF CHINA ARMS IND GRP
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