A Lightweight Fully Convolutional Neural Network for SAR Automatic Target Recognition

Author:

Yu Jimin,Zhou Guangyu,Zhou ShangboORCID,Yin Jiajun

Abstract

Automatic target recognition (ATR) in synthetic aperture radar (SAR) images has been widely used in civilian and military fields. Traditional model-based methods and template matching methods do not work well under extended operating conditions (EOCs), such as depression angle variant, configuration variant, and noise corruption. To improve the recognition performance, methods based on convolutional neural networks (CNN) have been introduced to solve such problems and have shown outstanding performance. However, most of these methods rely on continuously increasing the width and depth of networks. This adds a large number of parameters and computational overhead, which is not conducive to deployment on edge devices. To solve these problems, a novel lightweight fully convolutional neural network based on Channel-Attention mechanism, Channel-Shuffle mechanism, and Inverted-Residual block, namely the ASIR-Net, is proposed in this paper. Specifically, we deploy Inverted-Residual blocks to extract features in high-dimensional space with fewer parameters and design a Channel-Attention mechanism to distribute different weights to different channels. Then, in order to increase the exchange of information between channels, we introduce the Channel-Shuffle mechanism into the Inverted-Residual block. Finally, to alleviate the matter of the scarcity of SAR images and strengthen the generalization performance of the network, four approaches of data augmentation are proposed. The effect and generalization performance of the proposed ASIR-Net have been proved by a lot of experiments under both SOC and EOCs on the MSTAR dataset. The experimental results indicate that ASIR-Net achieves higher recognition accuracy rates under both SOC and EOCs, which is better than the existing excellent ATR methods.

Publisher

MDPI AG

Subject

General Earth and Planetary Sciences

Reference42 articles.

1. Introduction to Radar Target Recognition;Tait,2005

2. ATR performance using enhanced resolution SAR;Novak;Algorithms Synth. Aperture Radar Imag. III,1996

3. The automatic target-recognition system in SAIP;Novak;Linc. Lab. J.,1997

4. Template-based SAR ATR performance using different image enhancement techniques;Owirka;Algorithms Synth. Aperture Radar Imag. VI,1999

5. Automatic Target Recognition in Synthetic Aperture Radar Imagery: A State-of-the-Art Review

Cited by 17 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Voice Fence Wall: User-optional voice privacy transmission;Journal of Information and Intelligence;2024-03

2. Detection of SAR Image Multiscale Ship Targets in Complex Inshore Scenes Based on Improved YOLOv5;IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing;2024

3. A Novel Approach for Single-Shot Target Recognition by Matching Graph of Feature Pixels;Procedia Computer Science;2024

4. Design of Remote Sensing Image Automatic Target Recognition and Emergency Rescue Assistant System Based on Deep Learning;2023 International Conference on Internet of Things, Robotics and Distributed Computing (ICIRDC);2023-12-29

5. LSCB: a lightweight feature extraction block for SAR automatic target recognition and detection;International Journal of Remote Sensing;2023-04-18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3