NAOC Open IR  > 月球与深空探测研究部
Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images
Chen, Guandong1; Li, Yu1; Sun, Guangmin1; Zhang, Yuanzhi2,3
2017-10-01
发表期刊APPLIED SCIENCES-BASEL
卷号7期号:10
摘要Polarimetric synthetic aperture radar (SAR) remote sensing provides an outstanding tool in oil spill detection and classification, for its advantages in distinguishing mineral oil and biogenic lookalikes. Various features can be extracted from polarimetric SAR data. The large number and correlated nature of polarimetric SAR features make the selection and optimization of these features impact on the performance of oil spill classification algorithms. In this paper, deep learning algorithms such as the stacked autoencoder (SAE) and deep belief network (DBN) are applied to optimize the polarimetric feature sets and reduce the feature dimension through layer-wise unsupervised pre-training. An experiment was conducted on RADARSAT-2 quad-polarimetric SAR image acquired during the Norwegian oil-on-water exercise of 2011, in which verified mineral, emulsions, and biogenic slicks were analyzed. The results show that oil spill classification achieved by deep networks outperformed both support vector machine (SVM) and traditional artificial neural networks (ANN) with similar parameter settings, especially when the number of training data samples is limited.
文章类型Article
关键词Oil Spill Polarimetric Synthetic Aperture Radar (Sar) Deep Belief Network Autoencoder Remote Sensing
WOS标题词Science & Technology ; Physical Sciences ; Technology
资助者National Key Research and Development Program of China(2016YFB0501501) ; National Key Research and Development Program of China(2016YFB0501501) ; Natural Scientific Foundation of China(41471353 ; Natural Scientific Foundation of China(41471353 ; 41706201) ; 41706201) ; National Key Research and Development Program of China(2016YFB0501501) ; National Key Research and Development Program of China(2016YFB0501501) ; Natural Scientific Foundation of China(41471353 ; Natural Scientific Foundation of China(41471353 ; 41706201) ; 41706201)
DOI10.3390/app7100968
关键词[WOS]MEDITERRANEAN SEA ; NEURAL-NETWORKS ; SAR ; ALGORITHM
收录类别SCI
语种英语
资助者National Key Research and Development Program of China(2016YFB0501501) ; National Key Research and Development Program of China(2016YFB0501501) ; Natural Scientific Foundation of China(41471353 ; Natural Scientific Foundation of China(41471353 ; 41706201) ; 41706201) ; National Key Research and Development Program of China(2016YFB0501501) ; National Key Research and Development Program of China(2016YFB0501501) ; Natural Scientific Foundation of China(41471353 ; Natural Scientific Foundation of China(41471353 ; 41706201) ; 41706201)
WOS研究方向Chemistry ; Materials Science ; Physics
WOS类目Chemistry, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS记录号WOS:000414457800006
引用统计
被引频次:3[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.bao.ac.cn/handle/114a11/20216
专题月球与深空探测研究部
作者单位1.Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
2.Chinese Acad Sci, Natl Astron Observ, Beijing 100012, Peoples R China
3.Chinese Acad Sci, Key Lab Lunar Sci & Deep Space Explorat, Beijing 100012, Peoples R China
推荐引用方式
GB/T 7714
Chen, Guandong,Li, Yu,Sun, Guangmin,et al. Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images[J]. APPLIED SCIENCES-BASEL,2017,7(10).
APA Chen, Guandong,Li, Yu,Sun, Guangmin,&Zhang, Yuanzhi.(2017).Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images.APPLIED SCIENCES-BASEL,7(10).
MLA Chen, Guandong,et al."Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images".APPLIED SCIENCES-BASEL 7.10(2017).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Chen, Guandong]的文章
[Li, Yu]的文章
[Sun, Guangmin]的文章
百度学术
百度学术中相似的文章
[Chen, Guandong]的文章
[Li, Yu]的文章
[Sun, Guangmin]的文章
必应学术
必应学术中相似的文章
[Chen, Guandong]的文章
[Li, Yu]的文章
[Sun, Guangmin]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。