Research on Constant False Alarm Rate Detection Technique for Ship in SAR Image
-
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、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。Abstract: Among various methods to detect the ship targets in Synthetic Aperture Radar (SAR) image, the Constant False Alarm Rate (CFAR) detection algorithm with an adaptive detection threshold is the most important and extensively used one. In order to improve the detection performance for ships in SAR image, various statistical distributions are applied, with an attempt to accurately model the SAR clutter backgrounds, such as Gamma, K, log-normal, G0, the alpha-stable distribution, etc. In modern radar systems, the use of the CFAR technique is necessary to keep the false alarms at a suitably low rate in an a priori unknown time-varying and spatially nonhomogeneous backgrounds, and to improve the detection probability as much as possible. The clutter background in SAR images is complicated and variable, when the actual clutter background deviates from the assumed statistical distribution, the performance of the parametric CFAR detectors deteriorates, whereas the nonparametric CFAR method exhibits its advantage. In this paper, the Wilcoxon nonparametric CFAR scheme for ship detection in SAR image is proposed and analyzed. By comparison with several typical parametric CFAR schemes on 3 real SAR images of Radarsat-2, ICEYE-X6 and Gaofen-3, the robustness of the Wilcoxon nonparametric detector to maintain a good false alarm performance in these different detection backgrounds is revealed, and its detection performance for the weak ship is improved evidently. Moreover, the detection speed of the Wilcoxon nonparametric detector is fast, and it has the simplicity of hardware implementation.
-
Key words:
- SAR image /
- Radar clutter /
- Target detection /
- Constant False Alarm Rate(CFAR) /
- Nonparametric
-
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 Weibull-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. (查阅网上所有资料, 请补充页码) . [15] KVAM P H and VIDAKOVIC B. Nonparametric Statistics with Applications to Science and Engineering[M]. New Jersey: John Wiley & Sons, Inc. , 2007. (查阅网上所有资料, 请补充页码) . [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. (查阅网上所有资料,请补充本条文献内容) . [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. -
图(10) / 表(1)
计量
- 文章访问数: 80
- HTML全文浏览量: 126
- PDF下载量: 66
- 被引次数: 0
下载:
