SAR-AIRcraft-1.0:高分辨率SAR飞机检测识别数据集

王智睿 康玉卓 曾璇 汪越雷 张汀 孙显

王智睿, 康玉卓, 曾璇, 等. SAR-AIRcraft-1.0:高分辨率SAR飞机检测识别数据集[J]. 雷达学报, 2023, 12(4): 906–922. doi: 10.12000/JR23043
引用本文: 王智睿, 康玉卓, 曾璇, 等. SAR-AIRcraft-1.0:高分辨率SAR飞机检测识别数据集[J]. 雷达学报, 2023, 12(4): 906–922. doi: 10.12000/JR23043
WANG Zhirui, KANG Yuzhuo, ZENG Xuan, et al. SAR-AIRcraft-1.0: High-resolution SAR aircraft detection and recognition dataset[J]. Journal of Radars, 2023, 12(4): 906–922. doi: 10.12000/JR23043
Citation: WANG Zhirui, KANG Yuzhuo, ZENG Xuan, et al. SAR-AIRcraft-1.0: High-resolution SAR aircraft detection and recognition dataset[J]. Journal of Radars, 2023, 12(4): 906–922. doi: 10.12000/JR23043

SAR-AIRcraft-1.0:高分辨率SAR飞机检测识别数据集

doi: 10.12000/JR23043
基金项目: 国家自然科学基金(62076241, 62171436)
详细信息
    作者简介:

    王智睿,博士,副研究员,主要研究方向为SAR图像智能解译、多源协同感知

    康玉卓,博士生,主要研究方向为SAR图像智能解译

    曾 璇,博士生,主要研究方向为SAR图像智能解译、极化SAR地物要素分类等

    汪越雷,博士生,计算机视觉和模式识别、遥感图像解译

    张 汀,博士生,主要研究方向为计算机视觉和模式识别、遥感图像解译

    孙 显,博士,研究员,博士生导师,主要研究方向为计算机视觉与遥感图像理解

    通讯作者:

    孙显 sunxian@aircas.ac.cn

  • 责任主编:徐丰 Corresponding Editor: XU Feng
  • 中图分类号: TP753

SAR-AIRcraft-1.0: High-resolution SAR Aircraft Detection and Recognition Dataset

Funds: The National Natural Science Foundation of China (62076241, 62171436)
More Information
  • 摘要: 针对合成孔径雷达(SAR)图像中飞机散射点离散以及背景强干扰造成虚警的问题,该文提出了一种结合散射感知的SAR飞机检测识别方法。一方面,通过上下文引导的特征金字塔模块来增强全局信息,减弱复杂场景中强干扰的影响,提高检测识别的准确率。另一方面,利用散射关键点对目标进行定位,设计散射感知检测模块实现对回归框的细化校正,增强目标的定位精度。为了验证方法有效性、同时促进SAR飞机检测识别领域的研究发展,该文制作并公开了一个高分辨率SAR-AIRcraft-1.0数据集。该数据集图像来自高分三号卫星,包含4,368张图片和16,463个飞机目标实例,涵盖A220, A320/321, A330, ARJ21, Boeing737, Boeing787和other共7个类别。该文将提出的方法和常见深度学习算法在构建的数据集上进行实验,实验结果证明了散射感知方法的优异性能,并且形成了该数据集在SAR飞机检测、细粒度识别、检测识别一体化等不同任务中性能指标的基准。

     

  • 图  1  SAR飞机检测识别中的挑战

    Figure  1.  The challenges in SAR aircraft detection and recognition

    图  2  不同类别SAR飞机和光学飞机样本示例

    Figure  2.  SAR and optical aircrafts of different categories

    图  3  各个类别的实例数量

    Figure  3.  The quantity of each type of instances

    图  4  飞机目标的尺寸分布

    Figure  4.  The size distribution of aircraft targets

    图  5  数据集标注示意图

    Figure  5.  The annotated results in the dataset

    图  6  提出方法的整体结构

    Figure  6.  The overall structure of the proposed method

    图  7  上下文引导的特征金字塔网络结构

    Figure  7.  The framework of context-guided feature pyramid network

    图  8  散射感知检测头的结构

    Figure  8.  The structure of scattering-aware detection head

    图  9  可视化结果展示

    Figure  9.  The visualization results

    图  10  混淆矩阵示意图

    Figure  10.  The confusion matrices for the methods

    图  11  不同先进方法的F1曲线

    Figure  11.  F1 curves of different advanced methods

    图  12  不同模块的F1曲线

    Figure  12.  F1 curves of different improvements in the proposed method

    图  13  不同模块的PR曲线

    Figure  13.  PR curves of different improvements in the proposed method

    图  14  检测结果和可视化

    Figure  14.  Detection results and visualization

    图  15  SA-Net的检测结果

    Figure  15.  Detection results of SA-Net

    1  SAR-AIRcraft-1.0:高分辨率SAR飞机检测识别数据集发布网页

    1.  Release webpage of SAR-AIRcraft-1.0: High-resolution SAR aircraft detection and recognition dataset

    表  1  SAR-AIRcraft-1.0数据集与其他SAR目标检测识别数据集的比较

    Table  1.   Comparison between the SAR-AIRcraft-1.0 dataset and other SAR object detection datasets

    名称类别实例数量图片数量大小发布年份任务
    MSTAR105,9505,950128×1281998车辆识别
    OpenSARShip1711,34611,346256×2562017舰船检测识别
    SSDD12,4561,160190~6682017舰船检测
    SAR-Ship-Dataset159,53543,819256×2562019舰船检测
    AIR-SARShip-1.01461313000×30002019舰船检测
    HRSID116,9515,604800×8002020舰船检测和实例分割
    FUSAR-Ship1516,14416,144512×5122020舰船检测识别
    SADD17,8352,966224×2242022飞机检测
    MSAR-1.0460,39628,449256~20482022飞机、油罐、桥梁、舰船检测
    SAR-AIRcraft-1.0716,4634,368800~15002023飞机检测识别
    下载: 导出CSV

    表  2  不同方法的检测结果(%)

    Table  2.   The detection results of different methods (%)

    检测方法PRF1AP0.5AP0.75
    Faster R-CNN77.678.177.871.653.6
    Cascade R-CNN89.079.584.077.859.1
    Reppoints62.788.781.280.352.9
    SKG-Net57.688.869.979.851.0
    SA-Net87.582.284.880.461.4
    下载: 导出CSV

    表  3  不同类别实例目标的数量

    Table  3.   The number of instance targets of different categories

    类别训练集样本数量测试集样本数量总计
    A33027831309
    A320/3211719521771
    A22032704603730
    ARJ218253621187
    Boeing73720075502557
    Boeing78721914542645
    other322310414264
    总计13513295016463
    下载: 导出CSV

    表  4  细粒度识别结果(%)

    Table  4.   Fine-grained recognition results (%)

    方法 Acc (top-1/top-3)A330A320/321A220ARJ21Boeing737Boeing787other
    ResNet-5075.59/89.1974.1990.3878.0473.7661.6478.6380.50
    ResNet-10178.58/90.3793.5598.0876.9673.7671.8274.6784.82
    ResNeXt-5080.61/89.4683.8794.2378.9174.8673.2783.0485.40
    ResNeXt-10182.20/91.8387.1010080.8779.8371.0983.9287.70
    Swin Transformer81.29/92.5177.4210080.8774.5973.8286.1284.82
    下载: 导出CSV

    表  5  基于深度学习算法的检测结果(IoU=0.5)

    Table  5.   The performance of the algorithms based on deep learning (IoU=0.5)

    类别Faster
    R-CNN
    Cascade
    R-CNN
    ReppointsSKG-NetSA-Net
    A33085.087.489.879.388.6
    A320/32197.297.597.978.294.3
    A22078.574.071.466.480.3
    ARJ2174.078.073.065.078.6
    Boeing73755.154.555.765.159.7
    Boeing78772.968.351.869.670.8
    other70.169.168.471.471.3
    平均值(mAP)76.175.772.670.777.7
    下载: 导出CSV

    表  6  基于深度学习算法的检测结果(IoU=0.75)

    Table  6.   The performance of the algorithms based on deep learning (IoU=0.75)

    类别Faster
    R-CNN
    Cascade
    R-CNN
    ReppointsSKG-NetSA-Net
    A33085.087.466.466.488.6
    A320/32187.773.984.949.686.6
    A22058.749.149.429.855.0
    ARJ2155.259.050.937.759.7
    Boeing73742.839.136.648.741.8
    Boeing78760.557.641.851.660.4
    other45.446.143.141.147.7
    平均值(mAP)62.258.953.346.462.8
    下载: 导出CSV

    表  7  所提方法中各个模块的影响(%)

    Table  7.   Influence of each component in the proposed method (%)

    方法 PRF1AP0.5AP0.75
    Baseline88.181.284.579.660.7
    Baseline+SA-Head88.282.185.080.360.8
    Baseline+CG-FPN88.681.985.180.460.4
    SA-Net87.582.284.880.461.4
    下载: 导出CSV
  • [1] FU Kun, FU Jiamei, WANG Zhirui, et al. Scattering-keypoint-guided network for oriented ship detection in high-resolution and large-scale SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 11162–11178. doi: 10.1109/JSTARS.2021.3109469
    [2] GUO Qian, WANG Haipeng, and XU Feng. Scattering enhanced attention pyramid network for aircraft detection in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(9): 7570–7587. doi: 10.1109/TGRS.2020.3027762
    [3] SHAHZAD M, MAURER M, FRAUNDORFER F, et al. Buildings detection in VHR SAR images using fully convolution neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(2): 1100–1116. doi: 10.1109/TGRS.2018.2864716
    [4] ZHANG Zhimian, WANG Haipeng, XU Feng, et al. Complex-valued convolutional neural network and its application in polarimetric SAR image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(12): 7177–7188. doi: 10.1109/TGRS.2017.2743222
    [5] FU Kun, DOU Fangzheng, LI Hengchao, et al. Aircraft recognition in SAR images based on scattering structure feature and template matching[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(11): 4206–4217. doi: 10.1109/JSTARS.2018.2872018
    [6] DU Lan, DAI Hui, WANG Yan, et al. Target discrimination based on weakly supervised learning for high-resolution SAR images in complex scenes[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(1): 461–472. doi: 10.1109/TGRS.2019.2937175
    [7] CUI Zongyong, LI Qi, CAO Zongjie, et al. Dense attention pyramid networks for multi-scale ship detection in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 11: 8983–8997. doi: 10.1109/TGRS.2019.2923988
    [8] ZHANG Jinsong, XING Mengdao, and XIE Yiyuan. FEC: A feature fusion framework for SAR target recognition based on electromagnetic scattering features and deep CNN features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(3): 2174–2187. doi: 10.1109/TGRS.2020.3003264
    [9] ZHAO Yan, ZHAO Lingjun, LI Chuyin, et al. Pyramid attention dilated network for aircraft detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(4): 662–666. doi: 10.1109/LGRS.2020.2981255
    [10] ZHAO Yan, ZHAO Lingjun, LIU Zhong, et al. Attentional feature refinement and alignment network for aircraft detection in SAR imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5220616. doi: 10.1109/TGRS.2021.3139994
    [11] FU Jiamei, SUN Xian, WANG Zhirui, et al. An anchor-free method based on feature balancing and refinement network for multiscale ship detection in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(2): 1331–1344. doi: 10.1109/TGRS.2020.3005151
    [12] SUN Yuanrui, WANG Zhirui, SUN Xian, et al. SPAN: Strong scattering point aware network for ship detection and classification in large-scale SAR imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 1188–1204. doi: 10.1109/JSTARS.2022.3142025
    [13] 郭倩, 王海鹏, 徐丰. SAR图像飞机目标检测识别进展[J]. 雷达学报, 2020, 9(3): 497–513. doi: 10.12000/JR20020

    GUO Qian, WANG Haipeng, and XU Feng. Research progress on aircraft detection and recognition in SAR imagery[J]. Journal of Radars, 2020, 9(3): 497–513. doi: 10.12000/JR20020
    [14] 吕艺璇, 王智睿, 王佩瑾, 等. 基于散射信息和元学习的SAR图像飞机目标识别[J]. 雷达学报, 2022, 11(4): 652–665. doi: 10.12000/JR22044

    LYU Yixuan, WANG Zhirui, WANG Peijin, et al. Scattering information and meta-learning based SAR images interpretation for aircraft target recognition[J]. Journal of Radars, 2022, 11(4): 652–665. doi: 10.12000/JR22044
    [15] KANG Yuzhuo, WANG Zhirui, FU Jiamei, et al. SFR-Net: Scattering feature relation network for aircraft detection in complex SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5218317. doi: 10.1109/TGRS.2021.3130899
    [16] CHEN Jiehong, ZHANG Bo, and WANG Chao. Backscattering feature analysis and recognition of civilian aircraft in TerraSAR-X images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(4): 796–800. doi: 10.1109/LGRS.2014.2362845
    [17] SUN Xian, LV Yixuan, WANG Zhirui, et al. SCAN: Scattering characteristics analysis network for few-shot aircraft classification in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5226517. doi: 10.1109/TGRS.2022.3166174
    [18] KEYDEL E R, LEE S W, and MOORE J T. MSTAR extended operating conditions: A tutorial[C]. The SPIE 2757, Algorithms for Synthetic Aperture Radar Imagery III, Orlando, USA, 1996: 228–242.
    [19] 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
    [20] 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.
    [21] 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
    [22] 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
    [23] 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
    [24] 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
    [25] ZHANG Peng, XU Hao, TIAN Tian, et al. SEFEPNet: Scale expansion and feature enhancement pyramid network for SAR aircraft detection with small sample dataset[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 3365–3375. doi: 10.1109/JSTARS.2022.3169339
    [26] 陈杰, 黄志祥, 夏润繁, 等. 大规模多类SAR目标检测数据集-1.0[J/OL]. 雷达学报. https://radars.ac.cn/web/data/getData?dataType=MSAR, 2022.

    CHEN Jie, HUANG Zhixiang, XIA Runfan, et al. Large-scale multi-class SAR image target detection dataset-1.0[J/OL]. Journal of Radars. https://radars.ac.cn/web/data/getData?dataType=MSAR, 2022.
    [27] HU Jie, SHEN Li, and SUN Gang. Squeeze-and-excitation networks[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 7132–7141.
    [28] SUN Yuanrui, SUN Xian, WANG Zhirui, et al. Oriented ship detection based on strong scattering points network in large-scale SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5218018. doi: 10.1109/TGRS.2021.3130117
    [29] HUANG Lichao, YANG Yi, DENG Yafeng, et al. DenseBox: Unifying landmark localization with end to end object detection[J]. arXiv preprint arXiv: 1509.04874, 2015.
    [30] MIKOLAJCZYK K and SCHMID C. Scale & affine invariant interest point detectors[J]. International Journal of Computer Vision, 2004, 60(1): 63–86. doi: 10.1023/B:VISI.0000027790.02288.f2
    [31] OLUKANMI P O, NELWAMONDO F, and MARWALA T. K-means-MIND: An efficient alternative to repetitive k-means runs[C]. 2020 7th International Conference on Soft Computing & Machine Intelligence (ISCMI), Stockholm, Sweden, 2020: 172–176.
    [32] DAI Jifeng, QI Haozhi, XIONG Yuwen, et al. Deformable convolutional networks[C]. 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 764–773.
    [33] FAN Haoqiang, SU Hao, and GUIBAS L. A point set generation network for 3d object reconstruction from a single image[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 2463–2471.
    [34] 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.
    [35] 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.
    [36] GIRSHICK R. Fast R-CNN[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440–1448.
    [37] CAI Zhaowei and VASCONCELOS N. Cascade R-CNN: Delving into high quality object detection[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 6154–6162.
    [38] YANG Ze, LIU Shaohui, HU Han, et al. RepPoints: Point set representation for object detection[C]. 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea, 2019: 9656–9665.
    [39] XIE Saining, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 5987–5995.
    [40] LIU Ze, LIN Yutong, CAO Yue, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]. 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021: 9992–10002.
    [41] 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, Korea, 2019: 9626–9635.
  • 加载中
图(16) / 表(7)
计量
  • 文章访问数:  6304
  • HTML全文浏览量:  1769
  • PDF下载量:  717
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-04-17
  • 修回日期:  2023-06-27
  • 网络出版日期:  2023-07-17
  • 刊出日期:  2023-08-28

目录

    /

    返回文章
    返回