A Deep Learning Model to Extract Ship Size From Sentinel-1 SAR Images
文献类型：期刊论文
| 作者 | Ren, Yibin2,3; Li, Xiaofeng2,3; Xu, Huan1 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2022 |
| 卷号 | 60页码:14 |
| ISSN号 | 0196-2892 |
| 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 |
| 通讯作者 | Li, Xiaofeng(xiaofeng.li@ieee.org) |
| 英文摘要 | 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. |
| 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 |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000728266600101 |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/177455]  |
| 专题 | 海洋研究所_海洋环流与波动重点实验室 |
| 通讯作者 | Li, Xiaofeng |
| 作者单位 | 1.Jiangsu Ocean Univ, Sch Geomat & Marine Informat, Lianyungang 222005, Peoples R China 2.Chinese Acad Sci, Ctr Ocean Mega Sci, Qingdao 266071, Peoples R China 3.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China |
| 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. |
入库方式： OAI收割
来源：海洋研究所
浏览0
下载0
收藏0
其他版本
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。