二维码（扫一下试试看！） | | 基于深层次特征增强网络的SAR图像舰船检测 | | Ship Detection in SAR Images Based on Deep Feature Enhancement Network | | 投稿时间：2021-04-27 | | DOI：10.15918/j.tbit1001-0645.2021.004 | | 中文关键词:合成孔径雷达舰船检测卷积神经网络特征增强上下文信息 | | English Keywords:synthetic aperture radarship detectionconvolution neural networkfeature enhancementcontext information | | 基金项目:国家部委科研项目（LJ20191A040155） | | | 摘要点击次数:270 | | 全文下载次数:160 | | 中文摘要: | | 针对合成孔径雷达图像中舰船目标检测困难的问题，提出了一种基于深层次特征增强网络的多尺度目标检测框架.利用Darknet53提取原始图像特征，自上而下建立四尺度特征金字塔；特别设计基于注意力机制的特征融合结构，自下而上衔接相邻特征层，构建增强型特征金字塔；利用候选区域及其周边上下文信息为检测器计算分类置信度和目标分数提供更高质量的判定依据.所提算法在SSDD公开数据集和SAR-Ship自建数据集上的平均检测精度分别为94.43%和91.92%.实验结果表明，该算法设定合理且检测性能优越. | | English Summary: | | Aiming at the difficulty of ship target detection in synthetic aperture radar images, a multi-scale target detection framework based on deep feature enhancement network was proposed. Darknet53 was used to extract features from original images, and build a four-scale feature pyramid from top to bottom. A feature fusion structure based on attention mechanism was specially designed to connect adjacent feature layers from bottom to top, and rebuild enhanced feature pyramid. Then, the proposed method utilized the candidate region and its surrounding context information to provide a higher quality judgment basis for the detector to calculate the classification confidence and target score.The average detection precision of the proposed method on SSDD public data set and SAR-Ship self-built data set were 94.43% and 91.92% respectively. The experimental results show that the proposed network framework is reasonable and has superior detection performance. | | 查看全文查看/发表评论下载PDF阅读器 | |
王建中,徐浩楠,王洪枫,于子博.基于残差密集块和自编码网络的红外与可见光图像融合[J].北京理工大学学报（自然科学版）,2021,41(10):1077~1083.WANGJianzhong,XUHaonan,WANGHongfeng,YUZibo.InfraredandVisibleImageFu ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21张江霄,冯春辉,马金鑫,张斌,徐畅,李舟军,党莹.可任意花费的可传递电子现金系统[J].北京理工大学学报（自然科学版）,2019,39(3):283~289.ZHANGJiang-xiao,FENGChun-hui,MAJin-xin,ZHANGBin,XUChang,LIZhou-jun,DANG ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21王保宪,王哲,张宇峰,赵维刚,李义强,王凯.基于图像高维特征压缩映射的混凝土表面裂缝检测算法[J].北京理工大学学报（自然科学版）,2019,39(4):343~351.WANGBao-xian,WANGZhe,ZHANGYu-feng,ZHAOWei-gang,LIYi-qiang,WANGKai ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21刘连,王孝通.基于图像熵分块的压缩感知字典学习算法[J].北京理工大学学报（自然科学版）,2019,39(5):520~523.LIULian,WANGXiao-tong.DictionaryLearningAlgorithmforCompressed-SensingBasedontheEntrop ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21王超,刘美灵,刘振宇,马沁巍,汪远银.触发方式对低速相机采集图像时间准确度的影响[J].北京理工大学学报（自然科学版）,2019,39(6):632~637.WANGChao,LIUMei-ling,LIUZhen-yu,MAQin-wei,WANGYuan-yin.InfluenceofTrigg ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21姚国伟,张凤,曹建文,邓志均.基于有向图的运载火箭综合电子系统设计方法[J].北京理工大学学报（自然科学版）,2019,39(6):650~654.YAOGuo-wei,ZHANGFeng,CAOJian-wen,DENGZhi-jun.LaunchVehicleIntegratedElectron ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21胡忠铠,高昆,豆泽阳,周颖婕,巩学美.基于全变分正则最大后验估计的高光谱图像亚像元快速定位方法[J].北京理工大学学报（自然科学版）,2019,39(8):870~875.HUZhong-kai,GAOKun,DOUZe-yang,ZHOUYing-jie,GONGXue-mei.AFastMeth ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21韩先君,刘艳丽,杨红雨.基于生成对抗网络的人脸图像彩色化方法[J].北京理工大学学报（自然科学版）,2019,39(12):1285~1291.HANXian-jun,LIUYan-li,YANGHong-yu.FaceImageColorizationBasedonGenerativeAdvers ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21张健源,朱星星,张旭明.基于统计形变模型的多模医学图像非刚性配准方法研究[J].北京理工大学学报（自然科学版）,2019,39(S1):52~56.ZHANGJian-yuan,ZHUXing-xing,ZHANGXu-ming.StatisticalDeformationModelBasedNon ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21兰艳成,张旭明.基于电磁定位仪的超声图像中穿刺针实时跟踪软件开发[J].北京理工大学学报（自然科学版）,2019,39(S1):48~51.LANYan-cheng,ZHANGXu-ming.DevelopmentofReal-TimeTrackingSoftwareforPunctureNeedl ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21
| |
