An Aircraft Detection Method Based on Convolutional Neural Networks in High-Resolution SAR Images

Q2 Physics and Astronomy 雷达学报 Pub Date : 2017-04-01 DOI:10.12000/JR17009
Wang Siyu, Gao Xin, Sun Hao, Zheng Xin-wei, Sun Xian
{"title":"An Aircraft Detection Method Based on Convolutional Neural Networks in High-Resolution SAR Images","authors":"Wang Siyu, Gao Xin, Sun Hao, Zheng Xin-wei, Sun Xian","doi":"10.12000/JR17009","DOIUrl":null,"url":null,"abstract":"In the field of image processing using Synthetic Aperture Radar (SAR), aircraft detection is a challenging task. Conventional approaches always extract targets from the background of an image using image segmentation methods. Nevertheless, these methods mainly focus on pixel contrast and neglect the integrity of the target, which leads to locating the object inaccurately. In this study, we build a novel SAR aircraft detection framework. Compared to traditional methods, an improved saliency-based method is proposed to locate candidates coarsely and quickly in large scenes. This proposed method is verified to be more efficient compared with the sliding window method. Next, we design a convolutional neural network fitting in SAR images to accurately identify the candidates and obtain the final detection result. Moreover, to overcome the problem of limited available SAR data, we propose four data augmentation methods comprising translation, speckle noising, contrast enhancement, and small-angle rotation. Experimental results show that our framework achieves excellent performance on the high-resolution TerraSAR-X dataset.","PeriodicalId":37701,"journal":{"name":"雷达学报","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"33","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"雷达学报","FirstCategoryId":"1093","ListUrlMain":"https://doi.org/10.12000/JR17009","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Physics and Astronomy","Score":null,"Total":0}
引用次数: 33

Abstract

In the field of image processing using Synthetic Aperture Radar (SAR), aircraft detection is a challenging task. Conventional approaches always extract targets from the background of an image using image segmentation methods. Nevertheless, these methods mainly focus on pixel contrast and neglect the integrity of the target, which leads to locating the object inaccurately. In this study, we build a novel SAR aircraft detection framework. Compared to traditional methods, an improved saliency-based method is proposed to locate candidates coarsely and quickly in large scenes. This proposed method is verified to be more efficient compared with the sliding window method. Next, we design a convolutional neural network fitting in SAR images to accurately identify the candidates and obtain the final detection result. Moreover, to overcome the problem of limited available SAR data, we propose four data augmentation methods comprising translation, speckle noising, contrast enhancement, and small-angle rotation. Experimental results show that our framework achieves excellent performance on the high-resolution TerraSAR-X dataset.
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
基于卷积神经网络的高分辨率SAR图像飞机检测方法
在合成孔径雷达(SAR)图像处理领域,飞机检测是一项具有挑战性的任务。传统的方法总是使用图像分割方法从图像的背景中提取目标。然而,这些方法主要关注像素对比度,忽略了目标的完整性,导致目标定位不准确。在本研究中,我们构建了一个新的SAR飞机检测框架。与传统方法相比,提出了一种改进的基于显著性的方法,可以在大场景中快速粗略地定位候选对象。与滑动窗口方法相比,该方法被证明是更有效的。接下来,我们设计了一个卷积神经网络来拟合SAR图像,以准确识别候选图像并获得最终检测结果。此外,为了克服可用SAR数据有限的问题,我们提出了四种数据增强方法,包括平移、散斑噪声、对比度增强和小角度旋转。实验结果表明,我们的框架在高分辨率TerraSAR-X数据集上取得了优异的性能。
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
雷达学报
雷达学报 Physics and Astronomy-Instrumentation
CiteScore
4.10
自引率
0.00%
发文量
882
期刊介绍: Information not localized
期刊最新文献
Integrated Chip Technologies for Microwave Photonics Distributed Multi-target Localization System Based on Optical Wavelength Division Multiplexing Network A Novel Cluster-Analysis Algorithm Based on MAP Framework for Multi-baseline InSAR Height Reconstruction A Dynamic and Adaptive Selection Radar Tracking Method Based on Information Entropy An Aircraft Detection Method Based on Convolutional Neural Networks in High-Resolution SAR Images
×
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