Multitask Learning for Ship Detection From Synthetic Aperture Radar Images
文献类型：期刊论文
| 作者 | Zhang, Xin1,2 ; Huo, Chunlei1,2; Xu, Nuo1,2; Jiang, Hangzhi1,2; Cao, Yong1,2; Ni, Lei3; Pan, Chunhong1,2
|
| 刊名 | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
 |
| 出版日期 | 2021 |
| 卷号 | 14页码:8048-8062 |
| ISSN号 | 1939-1404 |
| 关键词 | Task analysis Feature extraction Radar polarimetry Object detection Marine vehicles Detectors Synthetic aperture radar Multitask learning synthetic aperture radar (SAR) SAR ship detection |
| DOI | 10.1109/JSTARS.2021.3102989 |
| 通讯作者 | Huo, Chunlei(clhuo@nlpria.ac.cn) |
| 英文摘要 | Ship detection from synthetic aperture radar (SAR) images is inherently subject to the special imaging mechanism of SAR. In recent years, deep-learning-based techniques for detecting objects from optical images have rapidly advanced and promoted the development of SAR image detection technology. However, the strong speckle noise in SAR images degrades low-level feature learning in shallow layers, hindering the higher level learning of semantic features for object detection. In view of the problems encountered in direct end-to-end feature learning for object detection and the close relationship between objects and auxiliary cues, a multitask learning-based object detector (MTL-Det) is proposed in this article to distinguish ships in SAR images. The proposed approach models the ship detection problem, not as a single object detection task, but as three cooperative tasks. The model involves two auxiliary subtasks that are focused on learning object-specific cues (e.g., texture and shape) for the ship detection task, which is constrained by the pseudoground truth generated by the main task. Assisted by auxiliary subtasks, the low-level features are robust to speckle noise and reliably support high-level feature learning. Compared with traditional single-task-based object detectors, more discriminative object-specific features are learned by multitask learning without the extra cost of manual labeling. The experiments conducted in this study help demonstrate the advantages of MTL-Det in improving the ship detection performance on two SAR datasets: high-resolution SAR images dataset and large-scale SAR ship detection dataset-v1.0. |
| WOS关键词 | TARGET DETECTION ; SAR IMAGES ; RESOLUTION |
| 资助项目 | National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[62076242] ; National Natural Science Foundation of China[61976208] ; National Key Research and Development Program of China[2018AAA0100400] |
| WOS研究方向 | Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000690441600006 |
| 资助机构 | National Natural Science Foundation of China ; National Key Research and Development Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/45890]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 通讯作者 | Huo, Chunlei |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Space Engn Univ, Grad Sch, Beijing 100192, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Xin,Huo, Chunlei,Xu, Nuo,et al. Multitask Learning for Ship Detection From Synthetic Aperture Radar Images[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2021,14:8048-8062. |
| APA | Zhang, Xin.,Huo, Chunlei.,Xu, Nuo.,Jiang, Hangzhi.,Cao, Yong.,...&Pan, Chunhong.(2021).Multitask Learning for Ship Detection From Synthetic Aperture Radar Images.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,14,8048-8062. |
| MLA | Zhang, Xin,et al."Multitask Learning for Ship Detection From Synthetic Aperture Radar Images".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 14(2021):8048-8062. |
入库方式： OAI收割
来源：自动化研究所
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。