Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

SAR (Synthetic Aperture Radar) image target identification method

A target recognition, image technology, applied in character and pattern recognition, instruments, computer parts, etc.

Inactive Publication Date: 2012-10-17
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a SAR image target recognition method in order to solve the above-mentioned problems existing in the existing SAR image target recognition

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 (Synthetic Aperture Radar) image target identification method
  • SAR (Synthetic Aperture Radar) image target identification method
  • SAR (Synthetic Aperture Radar) image target identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0045] The reconstruction algorithm using sparse representation can solve the coefficient vector α of sparse representation 0 , ideally, the coefficient vector α 0 In , only the coefficient of the i-th training sample of the same type as the target data may be non-zero, and the coefficients corresponding to other types of training samples are all 0, that is to say, the linear combination of the target data based on all training samples actually only depends on some of the same type Training samples.

[0046] However, due to the influence of imaging angle, noise interference, model error and other factors in practical applications, many relatively small non-zero coefficients are scattered to other classes. However, on the whole, there are still a large number of relatively large non-zero coefficients in the category to which the target data y ...

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 an SAR (Synthetic Aperture Radar) image target identification method. The method disclosed by the invention comprises the following steps of: utilizing a sparse representation theory to represent target data into linear combination of training samples; solving an optimization problem to obtain an approximate non-negative sparse coefficient with a distinguishable capability; and then, determining the type of the samples based on the size of the sum of various coefficients. The size of a training sample coefficient value reflects the similarity degree of the target data and the training samples; when the coefficient value is greater, the similarity is higher; otherwise, the similarity is lower; and therefore, in fact, the real category of the target data can be represented to the certain degree according to the size of the corresponding coefficient of the target data. Furthermore, a test image is guaranteed to be a non-negative weighted sum of each training sample through non-negative constraint, so that the test image has the meaning which can be better explained and is simultaneously good for identifying.

Description

technical field [0001] The invention belongs to the technical field of synthetic aperture radar (SAR, Synthetic Aperture Radar) automatic target recognition, and in particular relates to a SAR image target recognition method. Background technique [0002] Compared with ordinary optical imaging systems, SAR has strong imaging advantages for ground targets, especially ground stationary targets, and has received extensive attention and research as an important target detection method. With the continuous innovation and development of SAR imaging systems and methods, various SAR systems for different applications have begun to enrich, and the imaging functions and effects have also been continuously enhanced and improved. We have obtained a large amount of detection data by using these powerful imaging systems. These data not only provide us with more accurate and comprehensive detection results for targets, but also make people face the dilemma of how to timely and accurately e...

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): G06K9/62
Inventor 谢芳方庆段昶丁建松
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products