A Deep Learning Model to Extract Ship Size From Sentinel-1 SAR Images

doi:10.1109/TGRS.2021.3063216

IOCAS-IR > 海洋环流与波动重点实验室

	A Deep Learning Model to Extract Ship Size From Sentinel-1 SAR Images
	Ren, Yibin 1,2; Li, Xiaofeng 1,2; Xu, Huan 3
	2022
发表期刊	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
ISSN	0196-2892
卷号	60 页码:14
通讯作者	Li, Xiaofeng([email protected])
摘要	This study develops a deep learning (DL) model to extract the ship size from Sentinel-1 synthetic aperture radar (SAR) images, named SSENet. We employ a single shot multibox detector (SSD)-based model to generate a rotatable bounding box (RBB) for the ship. We design a deep-neural-network (DNN)-based regression model to estimate the accurate ship size. The hybrid inputs to the DNN-based model include the initial ship size and orientation angle obtained from the RBB and the abstracted features extracted from the input SAR image. We design a custom loss function named mean scaled square error (MSSE) to optimize the DNN-based model. The DNN-based model is concatenated with the SSD-based model to form the integrated SSENet. We employ a subset of the OpenSARShip, a data set dedicated to Sentinel-1 ship interpretation, to train and test SSENet. The training/testing data set includes 1500/390 ship samples. Experiments show that SSENet is capable of extracting the ship size from SAR images end to end. The mean absolute errors (MAEs) are under 0.8 pixels, and their length and width are 7.88 and 2.23 m, respectively. The hybrid input significantly improves the model performance. The MSSE reduces the MAE of length by nearly 1 m and increases the MAE of width by 0.03m compared to the mean square error (MSE) loss function. Compared with the well-performed gradient boosting regression (GBR) model, SSENet reduces the MAE of length by nearly 2 m (18.68x0025;) and that of width by 0.06 m (2.51x0025;). SSENet shows robustness on different training/testing sets.
关键词	Marine vehicles Radar polarimetry Feature extraction Synthetic aperture radar Data mining Radar imaging Oceans Custom loss function deep learning (DL) deep neural network (DNN) regression ship size extraction synthetic aperture radar (SAR) image
DOI	10.1109/TGRS.2021.3063216
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19060101]; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB42040401]; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19090103]; Key Research and Development Project of Shandong Province[2019JZZY010102]; Key Deployment Project of Center for Ocean Mega-Science; Chinese Academy of Sciences (CAS)[COMS2019R02]; China Postdoctoral Science Foundation[2019M662452]; CAS[Y9KY04101L]
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000728266600101
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：22[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/177456
专题	海洋环流与波动重点实验室
通讯作者	Li, Xiaofeng
作者单位	1.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China 2.Chinese Acad Sci, Ctr Ocean Mega Sci, Qingdao 266071, Peoples R China 3.Jiangsu Ocean Univ, Sch Geomat & Marine Informat, Lianyungang 222005, Peoples R China
第一作者单位	海洋环流与波动重点实验室
通讯作者单位	海洋环流与波动重点实验室
推荐引用方式 GB/T 7714	Ren, Yibin,Li, Xiaofeng,Xu, Huan. A Deep Learning Model to Extract Ship Size From Sentinel-1 SAR Images[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2022,60:14.
APA	Ren, Yibin,Li, Xiaofeng,&Xu, Huan.(2022).A Deep Learning Model to Extract Ship Size From Sentinel-1 SAR Images.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,60,14.
MLA	Ren, Yibin,et al."A Deep Learning Model to Extract Ship Size From Sentinel-1 SAR Images".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 60(2022):14.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
A_Deep_Learning_Mode（12529KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览