黄海宁,,
刘纪元,
刘正君,
韦琳哲
1.中国科学院声学研究所 北京 100190
2.中国科学院先进水下信息技术重点实验室 北京 100190
基金项目:国家自然科学基金(11904386),国家基础科研计划重大项目(JCKY2016206A003),中国科学院青年创新促进会(2019023)
详细信息
作者简介:李宝奇:男,1985年生,特别研究助理,研究方向为水声信号处理、目标检测、识别和跟踪、深度学习理论
黄海宁:男,1969年生,研究员,研究方向为水声信号与信息处理、目标探测、水声通信与网络等
刘纪元:男,1963年生,研究员,研究方向为水声信号处理、数字信号处理和水声成像与图像处理等
刘正君:女,1982年生,助理研究员,研究方向为水声信号处理等
韦琳哲:男,1991年生,助理研究员,研究方向为水声信号处理等
通讯作者:黄海宁 hhn@mail.ioa.ac.cn
中图分类号:TN959.72; TP391计量
文章访问数:261
HTML全文浏览量:103
PDF下载量:72
被引次数:0
出版历程
收稿日期:2020-12-14
修回日期:2021-05-29
网络出版日期:2021-08-27
刊出日期:2021-10-18
Synthetic Aperture Sonar Underwater Multi-scale Target Efficient Detection Model Based on Improved Single Shot Detector
Baoqi LI,Haining HUANG,,
Jiyuan LIU,
Zhengjun LIU,
Linzhe WEI
1. Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China
2. Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing, Chinese Academy of Sciences, Beijing 100190, China
Funds:The National Natural Science Foundation of China(11904386), The State Administration of Science, Technology and Industry Program (JCKY2016206A003), The Youth Innovation Promotion Association of Chinese Academy of Sciences (2019023)
摘要
摘要:针对轻量化目标检测模型SSD-MV2对合成孔径声呐(SAS)图像水下多尺度目标检测精度低的问题,该文提出一种新的卷积核模块-可扩张可选择模块(ESK),ESK具有通道可扩张、通道可选择和模型参数少的优点。与此同时,利用ESK模块重新设计了SSD的基础网络和附加特征提取网络,记作SSD-MV2ESK,并为其选择了合理的扩张系数和多尺度系数。在合成孔径声呐图像水下多尺度目标检测数据集SST-DET上,SSD-MV2ESK在模型参数基本相等的条件下,检测精度比SSD-MV2提升4.71%。实验结果表明,SSD-MV2ESK适用于合成孔径声呐图像水下多尺度目标检测任务。
关键词:合成孔径声呐/
图像水下多尺度目标检测/
SSD/
MobileNet V2/
多通道可选择/
深度可分离空洞卷积
Abstract:In view of the problem that the efficient detection model SSD-MV2 (Single Shot Detector MobileNet V2) has low detection accuracy to underwater multi-scale targets in Synthetic Aperture Sonar (SAS) images, a novel feature extraction module Extended Selective Kernel (ESK) is proposed in this paper. ESK has the advantages of channel scalability, channel selection and few model parameters. At the same time, the basic network and additional feature extraction network of SSD are redesigned by using ESK module, which is named SSD-MV2ESK, and a set of reasonable expansion coefficient and multi-scale coefficient are selected for SSD-MV2ESK. On SST-DET, the mAP of SSD-MV2ESK is 4.71% higher than that of SSD-MV2 when the model parameters are basically the same. The experimental results show that SSD-MV2ESK is suitable for SAR underwater multi-scale target detection task in embedded platform.
Key words:Synthetic Aperture Sonar (SAS)/
Underwater multi-scale target detection/
Single Shot Detector (SSD)/
MobileNet V2/
Channel selectable/
Depthwise separable dilated convolution
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=71cb35c8-be1d-4616-9c76-0bff36b2981a