RSDD-SAR:SAR舰船斜框检测数据集

徐从安 苏航 李健伟 刘瑜 姚力波 高龙 闫文君 汪韬阳

徐从安, 苏航, 李健伟, 等. RSDD-SAR:SAR舰船斜框检测数据集[J]. 雷达学报, 2022, 11(4): 581–599. doi: 10.12000/JR22007
引用本文: 徐从安, 苏航, 李健伟, 等. RSDD-SAR:SAR舰船斜框检测数据集[J]. 雷达学报, 2022, 11(4): 581–599. doi: 10.12000/JR22007
XU Congan, SU Hang, LI Jianwei, et al. RSDD-SAR: Rotated ship detection dataset in SAR images[J]. Journal of Radars, 2022, 11(4): 581–599. doi: 10.12000/JR22007
Citation: XU Congan, SU Hang, LI Jianwei, et al. RSDD-SAR: Rotated ship detection dataset in SAR images[J]. Journal of Radars, 2022, 11(4): 581–599. doi: 10.12000/JR22007

RSDD-SAR:SAR舰船斜框检测数据集

DOI: 10.12000/JR22007
基金项目: 国家自然科学基金(61790550, 61790554, 61971432, 62022092),中国科协青年人才托举工程基金(2020-JCJQ-QT-011),山东省泰山学者人才工程(tsqn201909156)
详细信息
    作者简介:

    徐从安(1987-),男,博士,副教授,主要研究方向为多平台多源预警探测、智能信息处理

    苏 航(1998-),男,海军航空大学在读硕士研究生,主要研究方向为SAR图像舰船目标检测

    李健伟(1989-),男,博士,工程师,主要研究方向为雷达与电子对抗、SAR图像智能处理、计算机视觉

    刘 瑜(1987-),男,博士,教授,主要研究方向为遥感图像处理、多模态数据融合

    姚力波(1980-),男,博士,副教授,主要研究方向为卫星遥感图像处理、目标检测与跟踪

    高 龙(1993-),男,博士,讲师,主要研究方向机器学习、异常检测、SAR图像智能处理

    闫文君(1986-),男,博士,副教授,主要研究方向为智能信息处理、频谱感知

    汪韬阳(1984-),男,博士,副研究员,主要研究方向为航天摄影测量、遥感图像几何处理、卫星视频目标检测与识别

    通讯作者:

    苏航 shpersonal_email@163.com

    李健伟 lgm_jw@163.com

  • 责任主编:孙显 Corresponding Editor: SUN Xian
  • 中图分类号: TN957.51; TN958

RSDD-SAR: Rotated Ship Detection Dataset in SAR Images

Funds: The National Natural Science Foundation of China (61790550, 61790554, 61971432, 62022092), The Young Elite Scientists Sponsorship Program by CAST (2020-JCJQ-QT-011), The Taishan Scholar Project of Shandong Province (tsqn201909156)
More Information
  • 摘要: 针对合成孔径雷达(SAR)舰船斜框检测数据集较少,难以满足算法发展和实际应用需求的问题,该文公开了SAR舰船斜框检测数据集(RSDD-SAR),该数据集由84景高分3号数据和41景TerraSAR-X数据切片及2景未剪裁大图,共127景数据构成,包含多种成像模式、多种极化方式、多种分辨率切片7000张,舰船实例10263个,通过自动标注和人工修正相结合的方式高效标注。同时,该文对几种常用的光学遥感图像斜框检测算法和SAR舰船斜框检测算法进行了实验,其中单阶段算法S2ANet检测效果最佳,平均精度达到90.06%。通过实验对比分析形成基准指标,可供相关学者参考。最后,该文通过泛化能力测试,分析讨论了RSDD-SAR数据集训练模型在其他数据集和未剪裁大图上的性能,结果表明:该数据集训练模型具有较好的泛化能力,说明该数据集具有较强的应用价值。RSDD-SAR数据集可在以下网址下载:https://radars.ac.cn/web/data/getData?dataType=SDD-SAR

     

  • 图  1  不同标注方式比较

    Figure  1.  Comparison of different annotation methods

    图  2  舰船目标航向和长宽比信息

    Figure  2.  The course and aspect ratio information of ship target

    图  3  斜框定义方式

    Figure  3.  Rotated bounding box definition method

    图  4  标注流程图

    Figure  4.  Annotation procedure

    图  5  数据预处理流程

    Figure  5.  Data preprocessing procedure

    图  6  数据切片方式

    Figure  6.  Data cutting method

    图  7  人工修正示例

    Figure  7.  Manual modification examples

    图  8  Google Earth纠正

    Figure  8.  Google Earth correction

    图  9  标注示例

    Figure  9.  Annotation example

    图  10  RSDD-SAR数据集结构

    Figure  10.  Structure of RSDD-SAR dataset

    图  11  数据集舰船角度和长宽比分布图

    Figure  11.  Angle and aspect ratio distribution maps of ships in RSDD-SAR dataset

    图  12  RSDD-SAR数据集典型场景

    Figure  12.  Typical scenarios in RSDD-SAR

    图  13  不同算法检测结果((a) 标注;(b) R-Faster R-CNN-ResNet-101检测结果;(c) RoI Transformer-ResNet-101检测结果;(d) Gliding Vertex-ResNet-101检测结果;(e) Oriented R-CNN-ResNet-101检测结果;(f) R-RetinaNet-ResNet-101检测结果;(g) S2ANet-ResNet-101检测结果;(h) R3Det-ResNet-101检测结果;(i) Redet-ReResNet-50检测结果;(j) DRBox-V2检测结果;(k) R-FCOS-ResNet-101检测结果;(l) CAF-ResNet-101检测结果;(m) Polar Encoding-ResNet-101检测结果)

    Figure  13.  Detection results of different methods ((a) Annotations; (b) Detection results of R-Faster R-CNN-ResNet-101; (c) Detection results of RoI Transformer-ResNet-101; (d) Detection results of Gliding Vertex-ResNet-101; (e) Detection results of Oriented R-CNN-ResNet-101; (f) Detection results of R-RetinaNet-ResNet-101; (g) Detection results of S2ANet-ResNet-101; (h) Detection results of R3Det-ResNet-101; (i) Detection results of Redet-ReResNet-50; (j) Detection results of DRBox-V2; (k) Detection results of R-FCOS-ResNet-101; (l) Detection results of CAF-ResNet-101; (m) Detection results of Polar Encoding-ResNet-101)

    图  14  SSDD数据集测试结果

    Figure  14.  Testing results on SSDD

    图  15  S2ANet AP50曲线

    Figure  15.  AP50 curves of S2ANet

    图  16  未剪裁大图测试

    Figure  16.  Testing on uncropped images

    1  RSDD-SAR数据集发布地址

    1.  Release address of RSDD-SAR dataset

    表  1  现有公开数据集详细信息

    Table  1.   Detailed information of existing public datasets

    数据集公开时间数据来源分辨率(m)图像尺寸图像数量任务
    OpenSARShip-1.0
    OpenSARShip-2.0
    2017Sentinel-12.7×22~
    3.5×22,
    20×22
    9×9~445×445
    1×1~445×445
    11346
    34528
    识别
    SSDD2017RadarSat-2
    TerraSAR-X
    Sentinel-1
    1~15190~6681160垂直边框检测
    斜框检测
    语义分割
    SAR-Ship-Dataset2019Gaofen-3
    Sentinel-1
    3~25256×25643918垂直边框检测
    AIR-SARShip-1.0
    AIR-SARShip-2.0
    2019Gaofen-31, 33000×3000
    1000×1000
    31
    300
    垂直边框检测
    FUSAR-Ship2020Gaofen-31.700×1.124~
    1.754×1.124
    512×5125243识别
    HRSID2021Sentinel-1
    TerraSAR-X
    0.5, 1.0, 3.0800×8005604垂直边框检测
    语义分割
    LS-SSDD-v1.02021Sentinel-15×2024000×1600015垂直边框检测
    SRSDD-v1.02021Gaofen-311024×1024666斜框检测
    识别
    RSDD-SAR2022Gaofen-3
    TerraSAR-X
    2~20512×5127000斜框检测
    下载: 导出CSV

    表  2  原始数据详细信息

    Table  2.   Detailed information of the raw data

    景号传感器经度纬度成像时间成像模式分辨率(m)极化方式产品级别入射角(°)成像幅宽(km)编号
    1GF-3E121.0N37.920171017FSII10HH,HVL1A19~501000-1
    下载: 导出CSV

    表  3  依据COCO划分标准RSDD-SAR舰船尺寸统计

    Table  3.   Area statistics of ships in RSDD-SAR according to COCO

    目标类型数量比例
    Small (area < 322)833181.17%
    Medium (322 < area < 962)192718.78%
    Large (area > 962)50.05%
    下载: 导出CSV

    表  4  依据文献[13]划分标准RSDD-SAR舰船尺寸统计

    Table  4.   Area statistics of ships in RSDD-SAR according to Ref. [13]

    目标类型数量比例
    Small (area < 625)614659.88%
    Medium (625 ≤ area ≤ 7500)410940.04%
    Large (area > 7500)80.08%
    下载: 导出CSV

    表  5  不同算法实验结果

    Table  5.   Experimental results of different algorithms

    模型骨干网络Params (M)FPSInshore AP50(%)Offshore AP50(%)AP50(%)
    两阶段R-Faster R-CNNResNet-10160.4513.2850.9991.4784.10
    ResNet-5041.4115.8748.7890.9383.29
    ResNet-1828.3022.3643.1888.5780.30
    RoI TransformerResNet-10174.378.1064.4094.8589.48
    ResNet-5055.3211.9360.8394.3588.39
    ResNet-1842.2113.7156.5193.3086.60
    Gliding VertexResNet-10160.4513.3262.2493.5088.16
    ResNet-5041.4116.8255.9391.6585.55
    ResNet-1828.2922.3351.4891.4984.63
    Oriented R-CNNResNet-10160.3421.9066.7790.2888.85
    ResNet-5041.3526.6065.9290.2188.84
    ResNet-1828.2834.3061.8290.0587.50
    ReDetReResNet-5031.5715.9061.9490.3488.40
    单阶段R-RetinaNetResNet-10151.4915.3335.7574.9267.89
    ResNet-5032.4422.3133.2074.0666.66
    ResNet-1819.3834.1530.1072.7465.09
    S2ANetResNet-10155.5015.7466.4394.9490.06
    ResNet-5036.4523.4663.2793.1487.91
    ResNet-1819.8532.0659.6192.5086.88
    R3DetResNet-10160.8024.1057.7390.0980.92
    ResNet-5041.8129.3056.8790.1680.87
    ResNet-1825.2537.6054.9289.6980.44
    DRBox-V2VGG1615.9128.2857.7991.2885.63
    无锚框R-FCOSResNet-10151.2118.8556.1793.7987.31
    ResNet-5032.1731.3950.0293.0985.48
    ResNet-1819.1142.0149.4892.3384.78
    CFAResNet-10155.8225.8067.3590.3389.46
    ResNet-5036.8336.6066.4090.4789.31
    ResNet-1820.2752.2067.3590.2788.97
    Polar EncodingResNet-10171.8316.7162.0289.9987.88
    ResNet-5052.8317.5659.6990.1287.31
    ResNet-1813.3627.4858.0589.3185.28
    下载: 导出CSV

    表  6  泛化能力测试

    Table  6.   Generalization ability testing results

    模型训练集验证集验证集AP50(%)测试集512×512
    AP50(%)
    测试集800×800
    AP50(%)
    S2ANet-ResNet-101RSDD-SAR训练集RSDD-SAR测试集90.0657.47(–32.59)63.04(–27.02)
    SSDD训练集SSDD测试集90.5236.24(–54.28)47.87(–42.65)
    S2ANet-ResNet-50RSDD-SAR训练集RSDD-SAR测试集87.9156.04(–31.87)63.15(–24.76)
    SSDD训练集SSDD测试集92.7341.81(–50.92)51.83(–40.90)
    S2ANet-ResNet-18RSDD-SAR训练集RSDD-SAR测试集86.8855.73(–31.15)62.04(–24.84)
    SSDD训练集SSDD测试集90.3034.52(–55.78)48.89(–41.41)
    下载: 导出CSV

    表  7  未剪裁大图测试结果

    Table  7.   Results on uncropped images

    模型训练集验证集验证集AP50(%)未剪裁大图AP50(%)
    S2ANet-ResNet-101RSDD-SAR训练集RSDD-SAR测试集90.0665.97(–24.09)
    SSDD训练集SSDD测试集90.5251.04(–39.48)
    下载: 导出CSV

    1  RSDD-SAR数据集详细信息

    1.   RSDD-SAR dataset information in detail

    景号传感器经度纬度时间成像模式分辨率(m)极化方式产品级别入射角(°)成像幅宽(km)编号
    1GF-3E121.0N37.920171017FSII10HH,HVL1A19~501000-1
    2GF-3E119.3N37.220210809UFS3DHL1A20~50302
    3GF-3E121.3N37.520180901FSI5HH,HVL1A19~50503-4
    4GF-3E120.5N37.920210228FSI5VH,VVL1A19~50505-6
    5GF-3E121.0N35.820210228FSI5VH,VVL1A19~50507-8
    6GF-3E119.1N38.220210619FSI5DVL1A19~50509
    7GF-3E120.5N37.820210526SS25HH,HVL1A17~5013010-11
    8GF-3E120.5N35.620210716SS25HH,HVL1A17~5013012-13
    9GF-3E122.9N37.520191231UFS3DHL1A20~503014
    10GF-3E119.8N35.020210228UFS3DHL1A20~503015
    11GF-3E119.8N35.320210228UFS3DHL1A20~503016
    12GF-3E120.4N37.920210228UFS3DHL1A20~503017
    13GF-3E120.9N37.920210718FSII10HH,HVL1A19~5010018-19
    14GF-3E120.3N36.020210305FSI5VH,VVL1A19~505020-21
    15GF-3E121.6N37.620210802FSI5HH,HVL1A19~505022-23
    16GF-3E122.5N37.520210130SS25VH,VVL1A17~5013024-25
    17GF-3E120.3N35.620210504SS25VH,VVL1A17~5013026-27
    18GF-3E120.6N36.220210519SS25HH,HVL1A17~5013028-29
    19GF-3E121.0N36.020210612SS25VH,VVL1A17~5013030-31
    20GF-3E121.5N38.220210612SS25VH,VVL1A17~5013032-33
    21GF-3E120.1N36.020210723SS25HH,HVL1A17~5013034-35
    22GF-3E120.6N38.120210723SS25HH,HVL1A17~5013036-37
    23GF-3E119.8N35.020210130UFS3DHL1A20~503038
    24GF-3E119.8N35.320210130UFS3DHL1A20~503039
    25GF-3E119.9N35.620210130UFS3DHL1A20~503040
    26GF-3E120.4N37.920210130UFS3DHL1A20~503041
    27GF-3E121.6N37.620210427UFS3DHL1A20~503042
    28GF-3E118.8N38.120210521UFS3DHL1A20~503043
    29GF-3E122.1N37.520210101FSI5VH,VVL1A19~505044-45
    30GF-3E121.1N35.820210113FSI5VH,VVL1A19~505046-47
    31GF-3E120.9N36.120210125FSI5VH,VVL1A19~505048-49
    32GF-3E120.3N38.220210204FSI5VH,VVL1A19~505050-51
    33GF-3E120.7N36.120210329SS25VH,VVL1A17~5013052-53
    34GF-3E119.6N37.920210417SS25VH,VVL1A17~5013054-55
    35TerraSAR-XE056N2720080311SL2HHSSC20~551056
    36TerraSAR-XE100N1320111209SM3HHMGD20~4530×5057
    37TerraSAR-XE013S0820190730SM3HHEEC20~4530×5058
    38TerraSAR-XW090N2920100516SM3HHEEC20~4530×5059
    39TerraSAR-XW090N2920120829SM3HHEEC20~4530×5060
    40TerraSAR-XW090N2920170807SM3HHSSC20~4530×5061
    41TerraSAR-XE023N3720180416SM3HHSSC20~4530×5062
    42TerraSAR-XE023N3720160830SM3HHSSC20~4530×5063
    43TerraSAR-XE023N3720170305SM3HHSSC20~4530×5064
    44TerraSAR-XE023N3720170623SM3HHSSC20~4530×5065
    45TerraSAR-XE023N3720170828SM3HHSSC20~4530×5066
    46TerraSAR-XE023N3720171022SM3HHSSC20~4530×5067
    47TerraSAR-XE023N3720171205SM3HHSSC20~4530×5068
    48TerraSAR-XE023N3720180209SM3HHSSC20~4530×5069
    49TerraSAR-XE023N3720180621SM3HHSSC20~4530×5070
    50TerraSAR-XE023N3720180815SM3HHSSC20~4530×5071
    51TerraSAR-XE023N3720181020SM3HHSSC20~4530×5072
    52TerraSAR-XE023N3720190127SM3HHSSC20~4530×5073
    53TerraSAR-XE023N3720190323SM3HHSSC20~4530×5074
    54TerraSAR-XE023N3720190619SM3HHSSC20~4530×5075
    55TerraSAR-XE023N3720190904SM3HHSSC20~4530×5076
    56TerraSAR-XE023N3720160614SM3HHSSC20~4530×5077
    57TerraSAR-XE121N3120151016SM3VVSSC20~4530×5078
    58TerraSAR-XE121N3120160614SM3VVSSC20~4530×5079
    59TerraSAR-XE121N3120160717SM3VVSSC20~4530×5080
    60TerraSAR-XE121N3120160819SM3VVSSC20~4530×5081
    61TerraSAR-XE121N3120151118SM3VVSSC20~4530×5082
    62TerraSAR-XE121N3120151210SM3VVSSC20~4530×5083
    63TerraSAR-XE121N3120160101SM3VVSSC20~4530×5084
    64TerraSAR-XE121N3120160203SM3VVSSC20~4530×5085
    65TerraSAR-XE121N3120160409SM3VVSSC20~4530×5086
    66TerraSAR-XE121N3120160512SM3VVSSC20~4530×5087
    67TerraSAR-XE119N3720151220SM3HHSSC20~4530×5088
    68TerraSAR-XE023N3720120305SM3HHSSC20~4530×5089
    69TerraSAR-XE023N3720120601SM3HHSSC20~4530×5090
    70TerraSAR-XE023N3720120908SM3HHSSC20~4530×5091
    71TerraSAR-XE023N3720121205SM3HHSSC20~4530×5092
    72TerraSAR-XE023N3720130314SM3HHSSC20~4530×5093
    73TerraSAR-XE023N3720151129SM3HHSSC20~4530×5094
    74TerraSAR-XE023N3720160225SM3HHSSC20~4530×5095
    75TerraSAR-XE023N3720160420SM3HHSSC20~4530×5096
    76GF-3E119.3N35.020200619FSII10HH,HVL1A19~5010097-98
    77GF-3E120.1N38.020200619FSII10HH,HVL1A19~5010099-100
    78GF-3E118.4N38.020200711FSII10HH,HVL1A19~50100101-102
    79GF-3E118.0N38.120200718FSII10HH,HVL1A19~50100103-104
    80GF-3E118.8N38.520200730FSII10HH,HVL1A19~50100105-106
    81GF-3E119.5N34.920200730FSII10HH,HVL1A19~50100107-108
    82GF-3E118.9N37.920200804FSII10HH,HVL1A19~50100109-110
    83GF-3E117.9N38.620200809FSII10HH,HVL1A19~50100111-112
    84GF-3E118.5N38.220200809FSII10HH,HVL1A19~50100113-114
    85GF-3E120.2N35.020201001FSII10VH,VVL1A19~50100115-116
    86GF-3E120.5N36.020201001FSII10VH,VVL1A19~50100117-118
    87GF-3E121.0N38.020201001FSII10VH,VVL1A19~50100119-120
    88GF-3E119.7N35.420200804FSI5HH,HVL1A19~5050121-122
    89GF-3E119.8N35.020200804FSI5HH,HVL1A19~5050123-124
    90GF-3E120.8N38.420201128FSI5VH,VVL1A19~5050125-126
    91GF-3E120.9N37.920201128FSI5VH,VVL1A19~5050127-128
    92GF-3E121.3N36.020201128FSI5VH,VVL1A19~5050129-130
    93GF-3E118.1N38.220200525FSI5HH,HVL1A19~5050131-132
    94GF-3E120.2N35.720200602SS25VH,VVL1A17~50130133-134
    95GF-3E119.5N35.720200711FSII10VH,VVL1A19~50100135-136
    96GF-3E118.8N38.320200728FSII10HH,HVL1A19~50100137-138
    97GF-3E119.6N35.320200728FSII10HH,HVL1A19~50100139-140
    98GF-3E120.2N35.420200519SS25VH,VVL1A17~50130141-142
    99GF-3E119.9N37.720200521SS25VH,VVL1A17~50130143-144
    100GF-3E120.2N35.820200521SS25VH,VVL1A17~50130145-146
    101GF-3E120.4N34.920200521SS25VH,VVL1A17~50130147-148
    102GF-3E121.0N35.820200502FSII10VH,VVL1A19~50100149-150
    103GF-3E120.5N35.920200509FSII10VH,VVL1A19~50100151-152
    104GF-3E120.0N38.520200514FSII10VH,VVL1A19~50100153-154
    105GF-3E120.0N38.320200729FSII10HH,HVL1A19~50100155-156
    106GF-3E120.6N36.020201006FSII10VH,VVL1A19~50100157-158
    107GF-3E122.8N37.220200924QPSI8HH,HV,VH,VVL1A20~4130159-162
    108GF-3E120.0N35.420201030QPSI8HH,HV,VH,VVL1A20~4130163-166
    109GF-3E119.1N37.420200814UFS3DHL1A20~5030167
    110GF-3E119.2N38.020200814UFS3DHL1A20~5030168
    111GF-3E120.1N37.820200926UFS3DHL1A20~5030169
    112GF-3E120.5N36.020200926UFS3DHL1A20~5030170
    113GF-3E121.3N37.720201121UFS3DHL1A20~5030171
    114GF-3E121.6N36.620201121UFS3DHL1A20~5030172
    115GF-3E120.0N38.520201104FSII10VH,VVL1A19~50100173-174
    116GF-3E121.1N35.820201126FSI5VH,VVL1A19~5050175-176
    117GF-3E121.5N37.720201126FSI5VH,VVL1A19~5050177-178
    118GF-3E121.4N38.120200519SS25VH,VVL1A17~50130179-180
    119GF-3E120.9N35.420200531SS25VH,VVL1A17~50130181-182
    120GF-3E119.8N37.920200619SS25VH,VVL1A17~50130183-184
    121GF-3E120.4N35.120200619SS25VH,VVL1A17~50130185-186
    122GF-3E120.3N34.820200704SS25VH,VVL1A17~50130187-188
    123GF-3E120.5N35.820200704SS25VH,VVL1A17~50130189-190
    124GF-3E121.9N37.720201011UFS3DHL1A20~5030191
    125GF-3E118.0N38.320201111UFS3DHL1A20~5030192
    126GF-3E119.8N35.220210619FSI5DVL1A19~5050GF3
    127TerraSAR-XE119N3720151128SM3HHSSC20~4530×50Terra
    下载: 导出CSV
  • [1] LI Jianwei, QU Changwen, and SHAO Jiaqi. Ship detection in SAR images based on an improved faster R-CNN[C]. 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA), Beijing, China, 2017: 1–6.
    [2] ZHANG Xiaohan, WANG Haipeng, XU Congan, et al. A lightweight feature optimizing network for ship detection in SAR image[J]. IEEE Access, 2019, 7: 141662–141678. doi: 10.1109/ACCESS.2019.2943241
    [3] ZHANG Tianwen, ZHANG Xiaoling, SHI Jun, et al. Depthwise separable convolution neural network for high-speed SAR ship detection[J]. Remote Sensing, 2019, 11(21): 2483. doi: 10.3390/rs11212483
    [4] ZHANG Peng, TANG Jinsong, ZHONG Heping, et al. Self-trained target detection of radar and sonar images using automatic deep learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 4701914. doi: 10.1109/TGRS.2021.3096011
    [5] 孙显, 王智睿, 孙元睿, 等. AIR-SARShip-1.0: 高分辨率SAR舰船检测数据集[J]. 雷达学报, 2019, 8(6): 852–862. doi: 10.12000/JR19097

    SUN Xian, WANG Zhirui, SUN Yuanrui, et al. AIR-SARShip-1.0: High-resolution SAR ship detection dataset[J]. Journal of Radars, 2019, 8(6): 852–862. doi: 10.12000/JR19097
    [6] WANG Yuanyuan, WANG Chao, ZHANG Hong, et al. A SAR dataset of ship detection for deep learning under complex backgrounds[J]. Remote Sensing, 2019, 11(7): 765. doi: 10.3390/rs11070765
    [7] WEI Shunjun, ZENG Xiangfeng, QU Qizhe, et al. HRSID: A high-resolution SAR images dataset for ship detection and instance segmentation[J]. IEEE Access, 2020, 8: 120234–120254. doi: 10.1109/ACCESS.2020.3005861
    [8] ZHANG Tianwen, ZHANG Xiaoling, KE Xiao, et al. LS-SSDD-v1.0: A deep learning dataset dedicated to small ship detection from large-scale Sentinel-1 SAR images[J]. Remote Sensing, 2020, 12(18): 2997. doi: 10.3390/RS12182997
    [9] LEI Songlin, LU Dongdong, QIU Xiaolan, et al. SRSDD-v1.0: A high-resolution SAR rotation ship detection dataset[J]. Remote Sensing, 2021, 13(24): 5104. doi: 10.3390/rs13245104
    [10] HUANG Lanqing, LIU Bin, LI Boying, et al. OpenSARShip: A dataset dedicated to Sentinel-1 ship interpretation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(1): 195–208. doi: 10.1109/JSTARS.2017.2755672
    [11] LI Boying, LIU Bin, HUANG Lanqing, et al. OpenSARShip 2.0: A large-volume dataset for deeper interpretation of ship targets in Sentinel-1 imagery[C]. 2017 SAR in Big Data Era: Models, Methods and Applications, Beijing, China, 2017: 1–5.
    [12] HOU Xiyue, AO Wei, SONG Qian, et al. FUSAR-Ship: Building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition[J]. Science China Information Sciences, 2020, 63(4): 140303. doi: 10.1007/s11432-019-2772-5
    [13] ZHANG Tianwen, ZHANG Xiaoling, LI Jianwei, et al. SAR ship detection dataset (SSDD): Official release and comprehensive data analysis[J]. Remote Sensing, 2021, 13(18): 3690. doi: 10.3390/rs13183690
    [14] European Space Agency[EB/OL]. https://www.esa.int/, 2022.
    [15] ITTVIS. ENVI-Image processing and analysis software solution[EB/OL]. https://www.ittvis.com/envi/, 2022.
    [16] PIE-SAR[EB/OL]. https://www.piesat.cn/product/PIE-SAR/index.html, 2022.
    [17] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The Pascal visual object classes (VOC) challenge[J]. International Journal of Computer Vision, 2010, 88(2): 303–338. doi: 10.1007/s11263-009-0275-4
    [18] HE Yishan, GAO Feo, WANG Jun, et al. Learning polar encodings for arbitrary-oriented ship detection in SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 3846–3859. doi: 10.1109/JSTARS.2021.3068530
    [19] RoLabelImg: Label rotated rect on images for training[EB/OL].https://github.com/cgvict/roLabelImg, 2022.
    [20] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context[C]. The 13th European Conference on Computer Vision, Zurich, Switzerland, 2014: 740–755.
    [21] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]. The 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 2015: 91–99.
    [22] REDMON J and FARHADI A. YOLO9000: Better, faster, stronger[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 6517–6525.
    [23] REDMON J and FARHADI A. YOLOv3: An incremental improvement[EB/OL]. https://arxiv.org/abs/1804.02767, 2018.
    [24] BOCHKOVSKIY A, WANG C Y, and LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection[EB/OL]. https://arxiv.org/abs/2004.10934, 2020.
    [25] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: Single shot MultiBox detector[C]. The 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 21–37.
    [26] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]. 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2999–3007.
    [27] ZHOU Xingyi, WANG Dequan, and KRÄHENBÜHL P. Objects as points[EB/OL]. http://arxiv.org/abs/1904.07850, 2019.
    [28] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: Fully convolutional one-stage object detection[C]. 2019 IEEE/CVF International Conference on Computer Vision, Seoul, South Korea, 2019: 9626–9635.
    [29] DING Jian, XUE Nan, LONG Yang, et al. Learning RoI transformer for oriented object detection in aerial images[C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 2844–2853.
    [30] XU Yongchao, FU Mingtao, WANG Qimeng, et al. Gliding vertex on the horizontal bounding box for multi-oriented object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(4): 1452–1459. doi: 10.1109/TPAMI.2020.2974745
    [31] XIE Xingxing, CHENG Gong, WANG Jiabao, et al. Oriented R-CNN for object detection[C]. 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021: 3500–3509.
    [32] HAN Jiaming, DING Jian, XUE Nan, et al. ReDet: A rotation-equivariant detector for aerial object detection[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Montreal, Canada, 2021: 2785–2794.
    [33] HAN Jiaming, DING Jian, LI Jie, et al. Align deep features for oriented object detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5602511. doi: 10.1109/TGRS.2021.3062048
    [34] YANG Xue, YAN Junchi, FENG Ziming, et al. R3Det: Refined single-stage detector with feature refinement for rotating object[C]. Thirty-Fifth AAAI Conference on Artificial Intelligence, Vancouver, Canada, 2021.
    [35] GUO Zonghao, LIU Chang, ZHANG Xiaosong, et al. Beyond bounding-box: Convex-hull feature adaptation for oriented and densely packed object detection[C]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, 2021: 8788–8797.
    [36] AN Quanzhi, PAN Zongxu, LIU Lei, et al. DRBox-v2: An improved detector with rotatable boxes for target detection in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(11): 8333–8349. doi: 10.1109/TGRS.2019.2920534
    [37] HU Shimin, LIANG Dun, YANG Guoye, et al. Jittor: A novel deep learning framework with meta-operators and unified graph execution[J]. Science China Information Sciences, 2020, 63(12): 222103. doi: 10.1007/s11432-020-3097-4
    [38] ZHOU Yue, YANG Xue, ZHANG Gefan, et al. MMRotate: A rotated object detection benchmark using PyTorch[EB/OL]. https://github.com/open-mmlab/mmrotate, 2022.
    [39] GOYAL P, DOLLÁR P, GIRSHICK R, et al. Accurate, large minibatch SGD: Training ImageNet in 1 hour[EB/OL]. https://arxiv.org/abs/1706.02677, 2018.
    [40] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770–778.
  • 加载中
图(17) / 表(8)
计量
  • 文章访问数:  6094
  • HTML全文浏览量:  4347
  • PDF下载量:  537
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-01-09
  • 修回日期:  2022-05-17
  • 网络出版日期:  2022-06-08
  • 刊出日期:  2022-08-28

目录

    /

    返回文章
    返回