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

Spectrum envelope feature-based radar target high-resolution range profile recognition method

A high-resolution range image and radar target technology, applied to radio wave measurement systems, instruments, etc., can solve problems such as large amount of calculation, difficulty in selection, and poor recognition effect, and achieve simple calculation, easy implementation, and dimensionality retention Effect

Inactive Publication Date: 2017-02-22
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of large amount of calculation, poor recognition effect due to loss of useful information and difficulty in selecting the most effective features in the above-mentioned prior art, the present invention provides a radar target high-resolution range profile recognition method based on spectral envelope features

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
  • Spectrum envelope feature-based radar target high-resolution range profile recognition method
  • Spectrum envelope feature-based radar target high-resolution range profile recognition method
  • Spectrum envelope feature-based radar target high-resolution range profile recognition method

Examples

Experimental program
Comparison scheme
Effect test

experiment example

[0075] The data used in the experiment is the high-resolution range image data collected by a domestic C-band ISAR radar in the field experiment of three aircraft (An, Cessna, Yak). Each aircraft contains 260 range images. In the experiment, the data of each aircraft is divided into 10 groups by sampling at equal intervals, that is, each group has 26 samples, and then 10 experiments are carried out respectively. In the first experiment, take the first group of each aircraft, a total of 26×3=78 range images as a template, and the other 9 groups, a total of 26×9×3=702 range images are used for testing, using the nearest neighbor method Carry out classification; in the second experiment, take the second group of each aircraft as a template, and the other 9 groups are used for testing; Finally, the results of 10 experiments are averaged to obtain the final recognition rate.

[0076] Table 1 shows the results of radar target recognition using the above five spectral envelope featu...

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 spectrum envelope feature-based radar target high-resolution range profile recognition method. A spectrum envelope is constructed based on the power spectrum of a target range profile; five feature attributes are extracted from the spectrum envelope, wherein the five feature attributes are brightness, irregularity, total power, the proportion of the sum of the power of fifth-order harmonic components to harmonic components of the highest order in the total power, and the proportion of the power of strongest spectrum components in the total power; the five feature attributes are combined together to form a five-dimensional spectrum envelope feature F5; two four-dimensional spectrum envelope features are constructed based on the spectrum envelope, wherein the two four-dimensional spectrum envelope features include harmonic components H4 of the first four orders and four strong spectrum components S4; the F5 feature is combined with the H4 feature and the S4 feature separately, so that two new 9-dimensional spectrum envelope features FH9 and FS9 can be obtained; and the above 5 spectrum envelope features are adopted to carry out radar target identification, and the validity of each feature is evaluated by using actually measured data. The method of the invention is simple in calculation and easy to implement, and is very suitable for the engineering application of radar target recognition. According to the method, the concept of the spectrum envelope is introduced.

Description

technical field [0001] The invention belongs to the technical field of radar, in particular to a target recognition method of a high-resolution range image of a radar target. Background technique [0002] The high-resolution range image of a radar target well reflects the radial distance distribution details and structural information of the target along the radar line of sight, which is of great value for target recognition and has the advantage of being easy to acquire and process. Recognition has become a research hotspot in the field of radar target recognition. [0003] The motion characteristics of the radar target cause the acquired range image to shift relative to the radar reference position, which makes the range image have translation sensitivity. Aiming at this problem, related literatures propose a variety of translation-invariant features for radar target recognition, among which, the power spectrum feature is widely used because of its simple and effective ca...

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): G01S7/41
CPCG01S7/411
Inventor 于雪莲郝英杰曲学超李海翔周云
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA