Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system for realizing noise suppression on ISAR miniature cluster target by using generative adversarial network

A noise suppression and network technology, applied in the field of target detection, can solve the problems of cluster target processing being too smooth, close targets overlapped together, and poor denoising effect, and achieve the effect of enhancing signal strength, good noise, and eliminating noise

Pending Publication Date: 2022-01-28
YANGTZE DELTA REGION INST OF UNIV OF ELECTRONICS SCI & TECH OF CHINE HUZHOU +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the existing technologies are based on traditional filtering algorithms. When this type of filtering algorithm is used for denoising micro-cluster targets, not only the de-noising effect is not good, but also the cluster targets are processed too smoothly, causing close-range targets to overlap.

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
  • Method and system for realizing noise suppression on ISAR miniature cluster target by using generative adversarial network
  • Method and system for realizing noise suppression on ISAR miniature cluster target by using generative adversarial network
  • Method and system for realizing noise suppression on ISAR miniature cluster target by using generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] The implementation of the noise suppression method for the ISAR micro-cluster target using the generation confrontation network provided by this embodiment includes the following steps:

[0067] 1. Analysis of ISAR micro-cluster target noise characteristics

[0068] Such as figure 1 as shown, figure 1 For the bird flock target signal after the range pulse pressure, the inverse synthetic aperture radar is used to detect the bird flock target at a long distance. It is relatively close, making it difficult to distinguish the number of targets, which will have a great impact on the noise in the subsequent target detection work. If the traditional filtering algorithm is used to suppress the noise, the signal of the flock of birds will be processed too smoothly, and the signals of multiple birds will be too smooth. overlap together.

[0069] 2. Bird flock signal simulation

[0070] Since it is difficult to obtain the noise-free condition of the micro-cluster target in the...

Embodiment 2

[0108] The system provided by this embodiment to realize the noise suppression system for the ISAR micro-cluster target by using the generative confrontation network includes a memory, a processor and data stored on the memory and can be processed by the processor, and the processor is provided with:

[0109] Against the network GAN; the described against the network GAN includes a generator and a discriminator;

[0110] The noisy simulation data generation unit is used to obtain the noisy simulation data and input it to the generator to obtain the first output G(z1), according to the first output G(z1) and the noise-free simulation data p data (x) is compared to participate in the generator loss, and compares the first output G(z1) with the noise-free simulated data p data (x) are all input to the discriminator for denoising discrimination, and the discriminant result of the discriminator is returned to the generator to participate in the loss;

[0111] The actual measuremen...

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 method and system for realizing noise suppression on an ISAR micro cluster target by using a generative adversarial network. The method comprises the following steps: constructing the generative adversarial network; inputting the noise simulation data into the generator to obtain a first output, comparing the first output with the noise-free simulation data to participate in generator loss, inputting the first output and the noise-free simulation data into a discriminator for denoising discrimination, and returning a discrimination result to participate in generator loss; inputting the measured data into the generator to obtain a second output, inputting the second output into the discriminator to obtain a discrimination result, and returning the discrimination result to participate in generator loss. According to the method provided by the invention, the actually measured data is added into the training process, and noise suppression can be realized while the bird flock signal intensity is enhanced. Noise can be well eliminated, the signal strength can be enhanced, and the range resolution is improved to a certain extent. And de-noising can be completed by using a small amount of simulation data. And the range resolution is improved to a certain extent.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a method and system for implementing noise suppression on ISAR micro-cluster targets by using a generative confrontation network. Background technique [0002] SAR moving target detection is widely used. For inverse synthetic aperture radar (ISAR: Inverse Synthetic Aperture Radar) ISAR noise suppression, an adaptive noise suppression method is usually used in the imaging process, and a threshold is set to filter the noise. Most of the remaining methods can only use traditional filtering algorithms. For example, the methods applied to SAR speckle noise suppression mainly include wavelet transform, Lee filtering, frost filtering, sigma filtering, gamma-map filtering and their improved algorithms. [0003] Most of the existing technologies are based on traditional filtering algorithms. When such filtering algorithms are used for denoising micro-cluster targets, not only the...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/088G06N3/045G06T5/70G01S13/9064G01S7/417G01S13/9027
Inventor 钱江叶鑫高建波唐文
Owner YANGTZE DELTA REGION INST OF UNIV OF ELECTRONICS SCI & TECH OF CHINE HUZHOU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com