期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 18, 期 7, 页码 1234-1238出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2020.2993899
关键词
Marine vehicles; Synthetic aperture radar; Detectors; Feature extraction; Convolution; Kernel; Hardware; Deep learning; lightweight network; ship detection; synthetic aperture radar (SAR)
类别
资金
- National Natural Science Foundation of China [61571099]
- National Key Research and Development Program of China [2017YFB0502700]
A lightweight SAR ship detector ShipDeNet-20 with 20 convolution layers and <1 MB model size is proposed to solve the issues of huge network scale and big model size. Experimental results show that ShipDeNet-20 outperforms other state-of-the-art object detectors in terms of accuracy and speed. Additionally, ShipDeNet-20 demonstrates strong migration ability on wide-region SAR images, beneficial for real-time SAR application and future hardware transplantation.
Existing most deep learning-based synthetic aperture radar (SAR) ship detectors have huge network scale and big model size. Thus, to solve these defects, we propose a lightweight SAR ship detector ShipDeNet-20 with 20 convolution layers and < 1 MB (0.82 MB) model size. We use fewer layers and kernels, and depthwise separable convolution (DS-Conv) to ensure ShipDeNet-20's lightweight attribute. Moreover, we also propose a feature fusion module (FF-Module), a feature enhance module (FE-Module), and a scale share feature pyramid module (SSFP-Module) to compensate for the raw ShipDeNet-20's accuracy loss. Experimental results on the open SAR ship detection data set (SSDD) reveal that the accuracy and speed of ShipDeNet-20 are both superior to the other nine state-of-the-art object detectors. Finally, detection results on another two wide-region SAR images show ShipDeNet-20's strong migration ability. ShipDeNet-20 is a novel SAR ship detector, built from scratch, lighter than others by tens even hundreds of times, helpful for real-time SAR application and future hardware transplantation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据