高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

SAR图像中舰船目标恒虚警率检测技术的研究

孟祥伟

孟祥伟. SAR图像中舰船目标恒虚警率检测技术的研究[J]. 电子与信息学报. doi: 10.11999/JEIT231436
引用本文: 孟祥伟. SAR图像中舰船目标恒虚警率检测技术的研究[J]. 电子与信息学报. doi: 10.11999/JEIT231436
MENG Xiangwei. Research on Constant False Alarm Rate Detection Technique for Ship in SAR Image[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT231436
Citation: MENG Xiangwei. Research on Constant False Alarm Rate Detection Technique for Ship in SAR Image[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT231436

SAR图像中舰船目标恒虚警率检测技术的研究

doi: 10.11999/JEIT231436
基金项目: 国家自然科学基金(62171402)
详细信息
    作者简介:

    孟祥伟:男,教授、博导,研究方向为雷达信号检测理论

    通讯作者:

    孟祥伟 mengxw163@sina.com

  • 中图分类号: TN957.51

Research on Constant False Alarm Rate Detection Technique for Ship in SAR Image

Funds: The National Natural Science Foundation of China (62171402)
  • 摘要: 在各种各样的合成孔径雷达图像舰船目标检测方法中,应用最广泛、最重要的就是具有自适应阈值的恒虚警率(CFAR)检测器。为了提高SAR图像中舰船目标的检测性能,人们试图通过各种统计分布模型对SAR图像中的杂波背景进行统计建模,如Gamma分布、K分布、对数正态分布、G0分布、alpha稳定分布等,再通过相应的统计分布模型以及各种样本筛选技术的CFAR检测器对舰船目标实施检测。SAR图像中杂波背景是复杂多变的,当实际杂波背景与假定统计分布失配时,参量型CFAR检测器的性能会恶化,非参数CFAR检测器就会显示出优势。该文提出了基于Wilcoxon非参数检测器的新途径对SAR图像中舰船目标进行检测,并在Radarsat-2, ICEYE-X6和Gaofen-3卫星的实测数据上,与几种典型的参量型CFAR检测方法进行了对比。实验结果表明,Wilcoxon非参数检测方法在这3种实测数据上的虚警控制能力具有良好的鲁棒性,还可以带来弱目标检测性能的改善,具有运算速度快、易于硬件实现的特点。
  • 图  1  Wilcoxon 非参数检测器的参考滑窗

    图  2  Radarsat-2的SAR 图像切片及几种检测器的检测结果

    图  3  几种检测器对图2(a)中白色圆圈中舰船目标检测结果的切片

    图  4  ICEYE-X6的SAR 图像切片及几种检测器的检测结果

    图  5  几种检测器对图4(a)中白色圆圈中舰船目标检测结果的切片

    图  6  Gaofen-3的SAR 图像切片及几种检测器的检测结果

    图  7  几种检测器对图6(a)中红色圆圈中弱舰船目标检测结果的切片

    图  8  几种检测器对弱舰船目标检测的ROC曲线

    图  9  Wilcoxon非参数检测器在检测单元t×t=3×3时的检测结果

    图  10  Wilcoxon检测器在t×t=3×3时对舰船目标的检测结果切片

    表  1  几种SAR图像舰船目标CFAR检测方法虚警性能的比较

    双参数CFAR 韦布尔-CFAR TS-CFAR AIS-RCFAR Wilcoxon方法
    图2(a)所示SAR图像 Nfa 102 106 122 118 26
    Nc 900 318 900 318 900 318 900 318 900 318
    Pfa(×10–4) 1.13 1.18 1.36 1.31 0.29
    PFA 1.0×10–7 3.0×10–5 1.0×10–4 3.0×10–6 1.0×10–8
    运算时间Ts(s) 30.86 311.17 382.35 66.50 12.83
    图4(a)所示SAR图像 Nfa 223 219 266 213 108
    Nc 2 481 960 2 481 960 2 481 960 2 481 960 2 481 960
    Pfa(×10–4) 0.90 0.88 1.07 0.86 0.44
    PFA 1.0×10–8 1.0×10–5 3.0×10–4 1.0×10–6 1.0×10–8
    运算时间Ts(s) 86.34 944.72 1196.44 546.77 56.54
    图6(a)所示SAR图像 Nfa 137 136 134 136 90
    Nc 1 320 909 1 320 909 1 320 909 1 320 909 1 320 909
    Pfa(×10–4) 1.04 1.03 1.01 1.03 0.68
    PFA 1.0×10–11 3.0×10–8 3.0×10–5 4.0×10–7 1.0×10–8
    运算时间Ts(s) 47.30 485.04 644.80 393.23 118.68
    下载: 导出CSV
  • [1] 杜兰, 王兆成, 王燕, 等. 复杂场景下单通道SAR目标检测及鉴别研究进展综述[J]. 雷达学报, 2020, 9(1): 34–54. doi: 10.12000/JR19104.

    DU Lan, WANG Zhaocheng, WANG Yan, et al. Survey of research progress on target detection and discrimination of single-channel SAR images for complex scenes[J]. Journal of Radars, 2020, 9(1): 34–54. doi: 10.12000/JR19104.
    [2] NOVAK L M, OWIRKA G J, and NETISHEN C M. Performance of a high-resolution polarimetric SAR automatic target recognition system[J]. The Lincoln Laboratory Journal, 1993, 6(1): 11–24.
    [3] LIAO Mingsheng, WANG Changcheng, WANG Yong, et al. Using SAR images to detect ships from sea clutter[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(2): 194–198. doi: 10.1109/LGRS.2008.915593.
    [4] GAO Gui, LIU Li, ZHAO Lingjun, et al. An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(6): 1685–1697. doi: 10.1109/TGRS.2008.2006504.
    [5] AI Jiaqiu, MAO Yuxiang, LUO Qiwu, et al. Robust CFAR ship detector based on bilateral-trimmed-statistics of complex ocean scenes in SAR imagery: A closed-form solution[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(3): 1872–1890. doi: 10.1109/TAES.2021.3050654.
    [6] MADJIDI H, LAROUSSI T, and FARAH F. A robust and fast CFAR ship detector based on median absolute deviation thresholding for SAR imagery in heterogeneous log-normal sea clutter[J]. Signal, Image and Video Processing, 2023, 17(6): 2925–2931. doi: 10.1007/s11760-023-02513-2.
    [7] TAO Ding, ANFINSEN S N, and BREKKE C. Robust CFAR detector based on truncated statistics in multiple-target situations[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1): 117–134. doi: 10.1109/TGRS.2015.2451311.
    [8] AI Jiaqiu, LUO Qiwu, YANG Xuezhi, et al. Outliers-robust CFAR detector of Gaussian clutter based on the truncated-maximum-likelihood-estimator in SAR imagery[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(5): 2039–2049. doi: 10.1109/TITS.2019.2911692.
    [9] ZEFREH R G, TABAN M R, NAGHSH M M, et al. Robust CFAR detector based on censored harmonic averaging in heterogeneous clutter[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(3): 1956–1963. doi: 10.1109/TAES.2020.3046050.
    [10] AI Jiaqiu, PEI Zhilin, YAO Baidong, et al. AIS data aided Rayleigh CFAR ship detection algorithm of multiple-target environment in SAR images[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(2): 1266–1282. doi: 10.1109/TAES.2021.3111849.
    [11] WANG Xinyang, LI Yang, and ZHANG Ning. A robust variability index CFAR detector for Weibull background[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(2): 2053–2064. doi: 10.1109/TAES.2022.3206256.
    [12] BAADECHE M and SOLTANI F. Closed-form expressions of PFA of mean level CFAR detectors for multiple-pulse gamma-distributed radar clutter[J]. Remote Sensing Letters, 2023, 14(10): 1054–1061. doi: 10.1080/2150704X.2023.2264491.
    [13] SAHED M, KENANE E, KHALFA A, et al. Exact closed-form Pfa expressions for CA- and GO-CFAR detectors in Gamma-distributed radar clutter[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(4): 4674–4679. doi: 10.1109/TAES.2022.3232101.
    [14] HÁJEK J, ŠIDÁK Z, and SEN P K. Theory of Rank Tests[M]. Now York: Academic Press, 1999.
    [15] KVAM P H and VIDAKOVIC B. Nonparametric Statistics with Applications to Science and Engineering[M]. New Jersey: John Wiley & Sons, Inc. , 2007.
    [16] RAVID R and LEVANON N. Maximum-likelihood CFAR for Weibull background[J]. IEE Proceedings F (Radar & Signal Processing), 1992, 139(3): 256–264. doi: 10.1049/ip-f-2.1992.0033.
    [17] https://www.iceye.com/downloads/datasets, 2023.
    [18] 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): 852–863. doi: 10.12000/JR19097.
  • 加载中
图(10) / 表(1)
计量
  • 文章访问数:  288
  • HTML全文浏览量:  288
  • PDF下载量:  164
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-12-28
  • 修回日期:  2024-06-13
  • 网络出版日期:  2024-06-19

目录

    /

    返回文章
    返回