SAR Target Recognition Using Improved Sparse Representation with Local Reconstruction

Li Ma,Bai Yuan Ding

doi:10.1155/2021/2446848

Abstract

In order to handle the problem of synthetic aperture radar (SAR) target recognition, an improved sparse representation-based classification (SRC) is proposed. According to the sparse coefficient vector resulting from the global dictionary, the largest coefficient in each class is taken as the reference. Then, the surrounding neighborhoods of the sample with the largest coefficient are selected to construct the optimal local dictionary in each training class. Afterwards, the samples in the local dictionary are used to reconstruct the test sample to be identified. Finally, the decision is made according to the comparison of the reconstruction errors from different classes. In the experiments, the proposed method is verified based on the moving and stationary target acquisition and recognition (MSTAR) dataset. The results show that the proposed method has performance advantages over existing methods, which demonstrates its effectiveness and robustness.

Highlights

Synthetic aperture radar (SAR) is capable of measuring highresolution images for effective ground observation and surveillance
In order to improve the comprehensive performance of SAR target recognition, researchers extensively use advanced image feature extraction and classification algorithms for experimentation and verification. ere are many types of features applied to SAR target recognition, including geometric shape features, projection transformation features, and electromagnetic scattering features. e geometric shape features describe the two-dimensional shape distribution of the target, such as area and contour [3,4,5,6,7,8,9,10]. e projection transformation features use mathematical projection or signal transformation algorithms to extract stable characteristics of the original images [11,12,13,14,15,16]
On the basis of the global sparse coefficients obtained from traditional Sparse representation-based classification (SRC), the local dictionary is constructed according to each training class

Summary

Introduction

Synthetic aperture radar (SAR) is capable of measuring highresolution images for effective ground observation and surveillance. In order to improve the comprehensive performance of SAR target recognition, researchers extensively use advanced image feature extraction and classification algorithms for experimentation and verification. In the global dictionary, the test sample is reconstructed by SRC, and the sparse coefficient vector is obtained. The test sample is optimally reconstructed on the local dictionaries from different classes to obtain their corresponding reconstruction errors. Wright et al first applied SRC in face recognition [31], that is, to determine the category of the test sample based on the reconstruction error of each class calculated based on the sparse representation coefficients. According to the solved sparse coefficient vector, the target class of the test sample can be judged according to its distributions in different classes. Due to the azimuthal sensitivity of SAR images, the training samples related to the test sample should share a similar azimuth angle. erefore, in order to obtain a better reconstruction result, the test sample should be reconstructed and analyzed on the local dictionary

Improvement of SRC for Target Recognition

Experiments

Method