SAR Target Model Recognition Method Based on Fusion Category Information and Local Preservation Projection

A technology that locally preserves projection and category information, applied in the field of image processing, can solve problems such as difficulty in implementation, achieve high recognition accuracy, overcome the problem of azimuth-sensitive characteristics, and achieve the effect of capturing and accurate description

Active Publication Date: 2020-04-10
SHAANXI NORMAL UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Target model identification is intended to distinguish targets of the same type and different models. Model identification is more difficult to achieve than type identification

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
  • SAR Target Model Recognition Method Based on Fusion Category Information and Local Preservation Projection
  • SAR Target Model Recognition Method Based on Fusion Category Information and Local Preservation Projection
  • SAR Target Model Recognition Method Based on Fusion Category Information and Local Preservation Projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Reference figure 1 , The SAR target model recognition method based on fusion category information and local preservation projection of the present invention includes the following steps:

[0058] Step 1. Use the SAR imaging method to obtain images containing training sample targets under different azimuth angles for multiple training sample targets. As a training sample image, multiple training samples under different azimuth angles will be acquired for each training sample target The images are divided into the same sample category; the SAR imaging method is used to obtain the image containing the target to be recognized as a test sample image; among them, the training sample target and the target to be recognized have similar external characteristics, and the test sample image and the scene of the training sample image are obtained the same. For example, when the target to be recognized is an armored vehicle, multiple armored vehicles of different models are used as tra...

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 SAR target model recognition method based on fused category information and local preservation projection, using the prior category information of the target, through the construction of a similarity matrix and a difference matrix, to realize the accurate description of data local characteristics and difference characteristics, Then, the advantages of the two characteristics are complemented by fusion, and finally the comprehensive capture and accurate description of the data structure characteristics are realized, so that the data structure before and after dimensionality reduction is effectively maintained. The invention can overcome the problem that the existing method is sensitive to the azimuth angle of the SAR target, and can obtain high-precision target model recognition results.

Description

Technical field [0001] The invention belongs to the technical field of image processing, relates to a method for accurately identifying targets under a high-resolution SAR system, and can be used as a basis for further precise guidance and command automation. Background technique [0002] Synthetic Aperture Radar (SAR) is an active microwave imaging sensor that is almost unaffected by climatic conditions and can work around the clock and around the clock. It is widely used in civil and military fields. The SAR automatic target recognition technology dedicated to effectively detecting targets from complex ground scenes and recognizing the detected targets refers to the radar based on the target and background based on the detection and positioning of the target. The echo signal extracts the characteristics of the target, and finally realizes the judgment of the target's attribute, type or model. [0003] For target type recognition, scholars at home and abroad have proposed many ef...

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): G06K9/62
CPCG06F18/251G06F18/214
Inventor 刘明汪西莉武杰孙增国洪灵
Owner SHAANXI NORMAL 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