DSDet: A Lightweight Densely Connected Sparsely Activated Detector for Ship Target Detection in High-Resolution SAR Images | |
Sun, Kun1; Liang, Yi1; Ma, Xiaorui2; Huai, Yuanyuan1; Xing, Mengdao1 | |
刊名 | REMOTE SENSING |
2021-07-01 | |
卷号 | 13期号:14页码:21 |
关键词 | ship detection data augmentation lightweight anchor-free detector one-stage synthetic aperture radar (SAR) deep learning |
DOI | 10.3390/rs13142743 |
通讯作者 | Liang, Yi(yliang@xidian.edu.cn) |
英文摘要 | Traditional constant false alarm rate (CFAR) based ship target detection methods do not work well in complex conditions, such as multi-scale situations or inshore ship detection. With the development of deep learning techniques, methods based on convolutional neural networks (CNN) have been applied to solve such issues and have demonstrated good performance. However, compared with optical datasets, the number of samples in SAR datasets is much smaller, thus limiting the detection performance. Moreover, most state-of-the-art CNN-based ship target detectors that focus on the detection performance ignore the computation complexity. To solve these issues, this paper proposes a lightweight densely connected sparsely activated detector (DSDet) for ship target detection. First, a style embedded ship sample data augmentation network (SEA) is constructed to augment the dataset. Then, a lightweight backbone utilizing a densely connected sparsely activated network (DSNet) is constructed, which achieves a balance between the performance and the computation complexity. Furthermore, based on the proposed backbone, a low-cost one-stage anchor-free detector is presented. Extensive experiments demonstrate that the proposed data augmentation approach can create hard SAR samples artificially. Moreover, utilizing the proposed data augmentation approach is shown to effectively improves the detection accuracy. Furthermore, the conducted experiments show that the proposed detector outperforms the state-of-the-art methods with the least parameters (0.7 M) and lowest computation complexity (3.7 GFLOPs). |
资助项目 | National Natural Science Foundation of China[61971326] |
WOS关键词 | DATA AUGMENTATION ; CFAR DETECTION ; SURVEILLANCE |
WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
出版者 | MDPI |
WOS记录号 | WOS:000677163400001 |
资助机构 | National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/45557] |
专题 | 融合创新中心 |
通讯作者 | Liang, Yi |
作者单位 | 1.Xidian Univ, Natl Lab Radar Signal Proc, Xian 710071, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Sun, Kun,Liang, Yi,Ma, Xiaorui,et al. DSDet: A Lightweight Densely Connected Sparsely Activated Detector for Ship Target Detection in High-Resolution SAR Images[J]. REMOTE SENSING,2021,13(14):21. |
APA | Sun, Kun,Liang, Yi,Ma, Xiaorui,Huai, Yuanyuan,&Xing, Mengdao.(2021).DSDet: A Lightweight Densely Connected Sparsely Activated Detector for Ship Target Detection in High-Resolution SAR Images.REMOTE SENSING,13(14),21. |
MLA | Sun, Kun,et al."DSDet: A Lightweight Densely Connected Sparsely Activated Detector for Ship Target Detection in High-Resolution SAR Images".REMOTE SENSING 13.14(2021):21. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论