Improved Drone Classification Using Polarimetric Merged-Doppler Images

IF 4 3区 地球科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC IEEE Geoscience and Remote Sensing Letters Pub Date : 2021-11-01 DOI:10.1109/lgrs.2020.3011114
B. Kim, Hyunseong Kang, Seongwook Lee, Seong‐Ook Park
{"title":"Improved Drone Classification Using Polarimetric Merged-Doppler Images","authors":"B. Kim, Hyunseong Kang, Seongwook Lee, Seong‐Ook Park","doi":"10.1109/lgrs.2020.3011114","DOIUrl":null,"url":null,"abstract":"We propose a drone classification method for polarimetric radar, based on convolutional neural network (CNN) and image processing methods. The proposed method improves drone classification accuracy when the micro-Doppler signature is very weak by the aspect angle. To utilize received polarimetric signal, we propose a novel image structure for three-channel image classification CNN. To reduce the size of data from four different polarization while securing high classification accuracy, an image processing method and structure are introduced. The data set is prepared for a three type of drone, with a polarimetric Ku-band frequency modulated continuous wave (FMCW) radar system. Proposed method is tested and verified in an anechoic chamber environment for fast evaluation. A famous CNN structure, GoogLeNet, is used to evaluate the effect of the proposed radar preprocessing. The result showed that the proposed method improved the accuracy from 89.9% to 99.8%, compared with single polarized micro-Doppler image. We compared the result from the proposed method with conventional polarimetric radar image structure and achieved similar accuracy while having half of full polarimetric data.","PeriodicalId":13046,"journal":{"name":"IEEE Geoscience and Remote Sensing Letters","volume":"18 1","pages":"1946-1950"},"PeriodicalIF":4.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/lgrs.2020.3011114","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Geoscience and Remote Sensing Letters","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1109/lgrs.2020.3011114","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 12

Abstract

We propose a drone classification method for polarimetric radar, based on convolutional neural network (CNN) and image processing methods. The proposed method improves drone classification accuracy when the micro-Doppler signature is very weak by the aspect angle. To utilize received polarimetric signal, we propose a novel image structure for three-channel image classification CNN. To reduce the size of data from four different polarization while securing high classification accuracy, an image processing method and structure are introduced. The data set is prepared for a three type of drone, with a polarimetric Ku-band frequency modulated continuous wave (FMCW) radar system. Proposed method is tested and verified in an anechoic chamber environment for fast evaluation. A famous CNN structure, GoogLeNet, is used to evaluate the effect of the proposed radar preprocessing. The result showed that the proposed method improved the accuracy from 89.9% to 99.8%, compared with single polarized micro-Doppler image. We compared the result from the proposed method with conventional polarimetric radar image structure and achieved similar accuracy while having half of full polarimetric data.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用偏振合并多普勒图像改进无人机分类
我们提出了一种基于卷积神经网络(CNN)和图像处理方法的极化雷达无人机分类方法。当微多普勒特征因方位角而很弱时,该方法提高了无人机的分类精度。为了利用接收到的极化信号,我们提出了一种新的三通道图像分类CNN的图像结构。为了减小来自四种不同偏振的数据的大小,同时确保高分类精度,介绍了一种图像处理方法和结构。该数据集是为三种类型的无人机准备的,该无人机具有极化Ku波段调频连续波(FMCW)雷达系统。为了快速评估,在消声室环境中对所提出的方法进行了测试和验证。使用著名的CNN结构GoogLeNet来评估所提出的雷达预处理的效果。结果表明,与单偏振微多普勒图像相比,该方法的精度从89.9%提高到99.8%。我们将所提出的方法的结果与传统的极化雷达图像结构进行了比较,并在具有一半全极化数据的情况下获得了类似的精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Geoscience and Remote Sensing Letters
IEEE Geoscience and Remote Sensing Letters 工程技术-地球化学与地球物理
CiteScore
7.60
自引率
12.50%
发文量
1113
审稿时长
3.4 months
期刊介绍: IEEE Geoscience and Remote Sensing Letters (GRSL) is a monthly publication for short papers (maximum length 5 pages) addressing new ideas and formative concepts in remote sensing as well as important new and timely results and concepts. Papers should relate to the theory, concepts and techniques of science and engineering as applied to sensing the earth, oceans, atmosphere, and space, and the processing, interpretation, and dissemination of this information. The technical content of papers must be both new and significant. Experimental data must be complete and include sufficient description of experimental apparatus, methods, and relevant experimental conditions. GRSL encourages the incorporation of "extended objects" or "multimedia" such as animations to enhance the shorter papers.
期刊最新文献
Target-driven Real-time Geometric Processing Based on VLR Model for LuoJia3-02 Satellite A “Difference In Difference” based method for unsupervised change detection in season-varying images On the Potential of Orbital VHF Sounding Radars to Locate Shallow Aquifers in Arid Areas Using Reflectometry A two-branch neural network for gas-bearing prediction using latent space adaptation for data augmentation-An application for deep carbonate reservoirs AccuLiteFastNet: A Remote Sensing Object Detection Model Combining High Accuracy, Lightweight Design, and Fast Inference Speed
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1