A Discriminant Feature Extraction Method for Rotor UAV and Bird Target Classification

A technology of unmanned rotor and target classification, which is applied in the field of target recognition, can solve the problems of classification performance degradation, achieve high classification rate, solve difficult identification, and avoid the effects of classification performance degradation

Active Publication Date: 2022-05-17
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The weighted principal component linear discriminant feature contains the micro-Doppler parameter characteristics of the target, without directly extracting physical parameters, avoiding the problem of inaccurate direct parameter extraction leading to the degradation of classification performance

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 Discriminant Feature Extraction Method for Rotor UAV and Bird Target Classification
  • A Discriminant Feature Extraction Method for Rotor UAV and Bird Target Classification
  • A Discriminant Feature Extraction Method for Rotor UAV and Bird Target Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The practicability of the present invention will be described below in combination with simulation experiments.

[0037] The simulation experiment designs single-rotor, quad-rotor, six-rotor, eight-rotor drones and flying bird targets. The simulated radar parameters include: the carrier frequency is 34.6GHz; the pulse repetition frequency is 125000Hz; the distance between the target and the radar is 100m; the pitch angle of the radar is 10°, and the azimuth angle is 45°. Aircraft parameters: Under initial conditions, the distance between the UAV and the radar is 100m, the speed of the UAV is 0, the number of blades of each rotor is 2, the distance from the tip of the blade to the center of rotation is 0.3m, and the distance from the tip of the blade to the center of rotation is 0.3m. The distance from the center is 0, the distance from each rotor rotation center to the axis center of the UAV is 0.4m, the rotational speed of the rotating parts is 30r / s, and the observati...

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 target recognition, and in particular relates to a discriminant feature extraction method in the classification of rotor drones and flying bird targets. The present invention first performs short-time Fourier transform on the radar echo data of the rotor UAV and flying birds to obtain the micro-Doppler spectrum data of the target, and then extracts the weighted principal component linearity of the target from the micro-Doppler spectrum Discriminant features to realize the classification of rotor UAV and flying bird targets. The present invention directly extracts the weighted principal component linear discriminant feature from the micro-Doppler spectrogram, avoiding the problem of classification performance degradation caused by inaccurate direct parameter extraction; in addition, the weighted principal component linear discriminant feature has the characteristics of noise insensitivity, In the case of low signal-to-noise ratio, it can still achieve a high correct classification rate, which solves the difficult problem of difficult identification of small and slow targets such as drones and birds.

Description

technical field [0001] The invention belongs to the technical field of target recognition, and in particular relates to a discriminant feature extraction method in the classification of rotor drones and flying bird targets. Background technique [0002] In recent years, due to the advantages of low cost, simple operation, and small size, UAVs have been widely used in military reconnaissance equipment detection, agricultural seeding and fertilization, forestry fire prevention monitoring, etc., and have good development prospects. But at the same time, unmanned drones flying into the aviation field to disrupt the order of the airport, and terrorists using drones to carry out terrorist attacks have caused harm to people's safety and the national economy. Therefore, accurately judging the type of UAV is of great significance to national air defense security. [0003] Both light and small UAVs and birds are typical "low, slow, small" targets. When radar is used for all-weather ...

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): G06V10/774G06K9/62G06K9/00G01S7/41
CPCG01S7/415G06F2218/04G06F2218/08G06F18/214Y02A90/10
Inventor 周代英晏钰坤骆军苏周爱霞
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