Sea surface target detection method based on fractal feature intelligent learning

A fractal feature and intelligent learning technology, which is applied in measuring devices, radio wave measurement systems, radio wave reflection/reradiation, etc., can solve problems such as poor spectral resolution, and achieve high accuracy and generalization capabilities

Active Publication Date: 2021-02-05
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But Fourier analysis implicitly adopts a seemingly natural assumption, that is, except for the observed data that can be obtained, other values ​​​​of the series are considered to be zero, but those of the series or its autocorrelation function we cannot The observed or unestimated values ​​are actually not all zero, and the spectral resolution obtained by Fourier analysis is poor

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 surface target detection method based on fractal feature intelligent learning
  • Sea surface target detection method based on fractal feature intelligent learning
  • Sea surface target detection method based on fractal feature intelligent learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0035] refer to figure 1 , the specific implementation process of the present invention is as follows:

[0036] Step 1. Divide the time series of radar echoes into several small sequences, and calculate the AR spectrum of each sea clutter sequence.

[0037] Let the sea clutter echo time series be X={X i ,i=1,2,3,...n}, calculate the AR spectrum S(f) of sea clutter:

[0038]

[0039] where a p,k is the AR coefficient, is the noise power, obtained by solving the Yule-walker equation in "AR-based Growler detection in seaclutter, IEEE trans. on Signal Processing, Vol.41, No.3, 1993".

[0040] Step 2, sea clutter AR spectrum joint fractal feature parameter calculation.

[0041] (a) For the AR spectrum sequence S(f) obtained in step 1, use the maximum value max(S(f)) of the sequence to normalize the AR spectrum sequence S(f) to obtain the sequence S...

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 surface target detection method based on fractal feature intelligent learning, and the method comprises the steps: learning a two-dimensional joint fractal feature parameter through employing a deep learning method, training a neural network for the intelligent discrimination of clutter and a target, and achieving the target detection. The AR spectrum estimation theory, the joint fractal characteristics and the deep learning method are combined, a novel intelligent method based on the AR spectrum joint fractal characteristics is provided for sea surface weak targetdetection, and the performance of weak target detection under the sea clutter background is improved. The defect that the detection performance of a traditional radar target detection method is reduced due to mismatch of a sea clutter model is overcome, the defects of traditional time domain and frequency domain fractal analysis are overcome, the influence of time correlation and frequency correlation on sea clutter fractal characteristic analysis is fully considered, and the sea surface weak target detection performance and stability are improved under the low signal-to-clutter ratio background; and the improved accuracy and generalization capability are realized.

Description

technical field [0001] The invention relates to the field of radar technology, in particular to an intelligent detection method for weak targets, which can be used for shore-based warning radars or sea search radars, by analyzing the joint fractal characteristics of AR spectrum between radar echo target units and sea clutter units The difference in parameters, combined with the intelligent method of deep learning, realizes the detection of weak targets on the radar sea surface, and has better detection performance in the case of low signal-to-clutter ratio. Background technique [0002] Sea clutter is the backscattered echoes of radar transmitted pulses illuminating the sea surface. The characteristic analysis and modeling simulation of sea clutter are very important for designing effective radar detection scheme and evaluating radar detection performance. The traditional research is mainly to study its statistical properties and establish a statistical distribution model. ...

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): G01S13/88G01S7/41
CPCG01S13/88G01S7/417G01S7/418Y02A90/10
Inventor 范一飞李浩江陶明亮粟嘉唐舒婷王伶张兆林李滔宫延云韩闯
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