Sea target intelligent detection method based on time-frequency three-feature extraction

A feature extraction and intelligent detection technology, applied in the field of radar, can solve the problems of insufficient recognition accuracy and achieve high accuracy and detection efficiency

Pending Publication Date: 2021-03-09
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to overcome the problem of insufficient recognition accuracy of the existing single-domain-based slow target detection method, the present invention uses the short-time Fourier analysis method to map the mixed echo data of the target and strong clutter to a two-dimensional plane of time and frequency With the help of the time-frequency characteristic difference between the target and the clutter, the refined feature extraction and robust target detection can be realized

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
  • Sea target intelligent detection method based on time-frequency three-feature extraction
  • Sea target intelligent detection method based on time-frequency three-feature extraction
  • Sea target intelligent detection method based on time-frequency three-feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0039] Step 1: time-frequency two-dimensional transformation;

[0040] Assuming that the radar echo signal to be tested is expressed as x(n), its short-time Fourier transform is expressed as:

[0041]

[0042] Among them, n and k are the number of discrete time sampling and discrete frequency sampling; h is the window function, using the Hamming window; m is the window length; N is the number of Fourier transform points;

[0043] Step 2: time-frequency feature extraction;

[0044] Firstly, the spectral function value in each time slice is accumulated along the time axis of the short-time Fourier transform, and the spectral function value T_E of the nth time slice is calculated n :

[0045]

[0046] The total short-time Fourier transform spectral function value E of the time-frequency plane is:

[0047]

[0048] On this basis, the following ...

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 provides a sea target intelligent detection method based on time-frequency three-feature extraction. Mixed echo data of a target and strong clutters are mapped into a two-dimensional plane of time and frequency by adopting a short-time Fourier analysis method, and refined feature extraction and steady target detection are realized by virtue of time-frequency characteristic differenceof the target and the clutters. Reliable target detection under a strong sea clutter background is realized by utilizing the difference of the target and the clutters and a machine learning method. The method effectively solves the problem that the target and the clutters are highly overlapped in a one-dimensional domain such as a time domain or a frequency domain and are difficult to separate, achieves the robust detection of a low-speed moving target in the time-frequency domain, and is higher in accuracy and detection efficiency.

Description

technical field [0001] The invention relates to the technical field of radar, and relates to a detection method based on three time-frequency features, which is applicable to the detection of slow-moving targets under complex clutter backgrounds. Background technique [0002] The research on ground / sea clutter background target detection has gone from simple to complex, and the dimension of signal processing has been continuously expanded, from single-domain processing of time, frequency, and space, to two-dimensional processing of time-frequency, space-time, and then to space-time The development of time-frequency multi-domain processing. In terms of radar maritime target detection technology, fixed threshold detection was proposed in the 1940s. However, with the increasingly complex background environment, in order to meet the requirements of radar for false alarm rate control, constant false alarm rate detection technology was proposed and gradually applied. into the rad...

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
IPC IPC(8): G01S13/02G01S7/41G06F17/14
CPCG01S13/02G01S7/418G06F17/14Y02A90/10
Inventor 粟嘉方丹陶明亮范一飞李滔宫延云王伶张兆林
Owner NORTHWESTERN POLYTECHNICAL 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