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

A SAR Target Classification Method Based on Sagan Sample Expansion and Auxiliary Information

A technology of auxiliary information and target classification, which is applied in the field of synthetic aperture radar small-sample target recognition, and can solve the problems of SAR small-sample data volume and so on

Active Publication Date: 2022-05-31
HARBIN ENG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problem of target areas in SAR remote sensing images. Based on the generation confrontation network, a network more suitable for SAR remote sensing images is proposed, so that the characteristics of different types of target areas can be learned, so as to generate new and more realistic targets. Regional image, which solves the problem of small amount of data in SAR small samples

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 SAR Target Classification Method Based on Sagan Sample Expansion and Auxiliary Information
  • A SAR Target Classification Method Based on Sagan Sample Expansion and Auxiliary Information
  • A SAR Target Classification Method Based on Sagan Sample Expansion and Auxiliary Information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described below in conjunction with the accompanying drawings.

[0057] A SAR target classification method based on SAGAN sample expansion and auxiliary information, comprising the following steps:

[0058] 1. Input the noise z of noise(z) into the sample generator network with a self-attention mechanism to obtain a data image imitating real samples. It is processed through four similar modules L1, L2, L3, and L4 with different scales in turn. Each module contains convolution, spectral normalization, ReLU activation, and three data processing layers in turn. After passing through L3 and L4, each enters a scale Different self-attention mechanism layers, and then output image labels after passing through a convolutional layer and Tanh activation layer.

[0059] Deconvolution is to convolve the initial input small data (noise), and the size becomes larger.

[0060] The first is to invert the convolution kernel. Then the convolution ...

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 field of synthetic aperture radar small-sample target recognition, in particular to a SAR target classification method based on SAGAN sample expansion and auxiliary information. In this study, according to the characteristics of SAR data sample images, the Inception structure is optimized and improved, and appropriate regularization conditions are added, combined with the above-mentioned results of GAN small sample generation and GAN small sample super-resolution, the SAR small sample target precise identification. The present invention proposes a network more suitable for SAR remote sensing images, enabling it to learn the characteristics of different types of target areas, thereby generating new and more realistic target area images, and solving the problem of small amount of data in small SAR samples. Aiming at the target area in the synthetic aperture radar SAR remote sensing image, a SAR target classification method based on self-attention generative confrontation network sample expansion and auxiliary information is solved. The invention mainly relates to a generative confrontation network to expand SAR new sample data, and Based on the Restnet50 structure network for SAR small sample target recognition.

Description

technical field [0001] The invention belongs to the field of synthetic aperture radar small-sample target recognition, in particular to a SAR target classification method based on SAGAN sample expansion and auxiliary information. Background technique [0002] Synthetic aperture radar, or SAR, is an active microwave imaging sensor. By transmitting broadband signals and combining synthetic aperture technology, SAR can simultaneously obtain two-dimensional high-resolution images in both range and azimuth directions. Compared with traditional optical remote sensing and hyperspectral remote sensing, SAR has all-weather and all-weather imaging capabilities, and has a certain degree of penetration. The obtained images can reflect the microwave scattering characteristics of the target. technical means. SAR has been widely used in the fields of military and people's livelihood, and it is an important technical means to realize space military reconnaissance, natural resource census, ...

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): G06K9/62G06N3/04G06N3/08
Inventor 关键刘加贝孙建国王嘉岐吴嘉恒袁野
Owner HARBIN ENG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com