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

SAR Target Recognition Method Based on Azimuth Correlation Dynamic Dictionary Sparse Representation

A dynamic dictionary and object recognition technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of insufficient recognition processing efficiency, target recognition accuracy, and complicated operation process, so as to improve recognition processing efficiency and reduce calculation amount , Solve the complicated effect of sparse coding and sparse reconstruction operation process

Active Publication Date: 2019-05-31
CHONGQING UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned problems in the prior art, the present invention provides a SAR target recognition method based on the sparse representation of the azimuth-related dynamic dictionary, which can improve the recognition processing efficiency and recognition accuracy of radar target recognition based on SAR images, for Solve the problems of complicated sparse coding and sparse reconstruction operation process, insufficient recognition processing efficiency and target recognition accuracy in the SAR target recognition method using sparse representation classification in the prior art

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 Recognition Method Based on Azimuth Correlation Dynamic Dictionary Sparse Representation
  • SAR Target Recognition Method Based on Azimuth Correlation Dynamic Dictionary Sparse Representation
  • SAR Target Recognition Method Based on Azimuth Correlation Dynamic Dictionary Sparse Representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0078] This embodiment uses the MSTAR database to do the experiment, which is the measured data obtained by the SAR system of the X-band of the San Diego National Laboratory in the United States. It has a resolution of 0.3m × 0.3m, and the pixel density of each SAR image is 128 Rows × 128 columns, collected at azimuth angles from 0° to 360°. Use BMP2 (infantry tank), BTR70 (armored personnel carrier), T72 (T-72 type main station tank) in the MSTAR database to carry out experiments in this embodiment, three different types of radar targets of BMP2, BTR70, T72 The visible light images of figure 2 (2a), (2b), (2c), and the SAR images of three different types of radar targets BMP2, BTR70, and T72 are as follows image 3 In (3a), (3b), (3c) shown. In this embodiment, part of the SAR image data of each type of target with an azimuth angle of 0° to 360° is used as training sample data, and the rest of the SAR image data is used as test sample data. The number of training samples ...

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 present invention provides a SAR target recognition method based on the sparse representation of the azimuth-related dynamic dictionary. It first estimates the azimuth of the SAR image as the test sample, and then calculates a relevant azimuth range according to the azimuth estimation value, thereby based on each A sparse feature training sample set composed of a collection of sparse feature matrices of training samples, the sparse feature matrix of the training samples whose azimuth values ​​are outside the range of the relevant azimuth angle in the sparse feature training sample set is set to a zero matrix, and only the azimuth angle is retained The sparse feature matrix of the training sample whose value is within the range of the relevant azimuth angle constitutes the sparse feature azimuth angle-related dynamic dictionary corresponding to the test sample, and then performs sparse representation classification and recognition, which greatly reduces the calculation of sparse coding and sparse reconstruction. The recognition processing efficiency is improved, and the interference of the training samples with irrelevant azimuth angles on the target recognition of the test samples is also reduced, so that the recognition accuracy is also improved.

Description

technical field [0001] The invention relates to the technical field of radar target recognition, in particular to a SAR target recognition method based on sparse representation of an azimuth-related dynamic dictionary. Background technique [0002] Synthetic Aperture Radar (SAR) technology is a pulse radar technology that uses mobile radar mounted on satellites or aircraft to obtain radar target images in high-precision geographic areas. Synthetic aperture radar is an active microwave imaging system, which can provide high-resolution images of the target area by irradiating the target area with electromagnetic waves and analyzing the echo signals. It has all-weather, all-day working ability and certain penetration ability. In view of its advantages, it is widely used in fields such as mineral exploration, marine environment monitoring and military defense. In the field of military defense, the research on target recognition is the most extensive, so the research on SAR Aut...

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
CPCG06F18/213G06F18/214G06F18/24
Inventor 张新征王亦坚谭志颖
Owner CHONGQING UNIV
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