A synthetic aperture radar sea surface distribution estimation by n-order Bézier curve and its application in ship detection
-
摘要: 迄今为止,大多数单极化合成孔径雷达图像的船只检测都采用恒虚警率方法。检测器的性能取决于两个方面:精确的海表面分布估计和精心设计的恒虚警率检测算法。首先,发展了一种新的基于n阶Bézier曲线的非参数海表面分布估计方法,推导了基于最小平方优化的解析解,给出了两个核心参数Bézier曲线的阶数n和采样点数量m的优选结果。进而,为了评价基于所提出方法的船只检测性能,将估计的海表面分布模型与单元平均恒虚警率算法相结合构建了新的船只检测器。为了排除背景窗口中可能的干扰,采用了改进的自动筛选算法。实验结果表明:(1)在海表面拟合性能方面,所提出的方法与传统的Parzen窗核方法同样好,在多数情况下,优于两种广泛使用的参数模型:和模型;(2)在计算速度方面,所提出方法的主要优势在于时间消耗仅取决于采样点数量,而与图像大小无关,因此相比于Parzen窗核方法,计算速度得到极大的提升。在某些情况下,甚至比两种参数方法还要快。(3)在船只检测方面,所提出方法构建的检测器对不同的合成孔径雷达,不同分辨率,不同的海表面均匀度具有很好的适应性,在测试集中表现优异。Abstract: To dates, most ship detection approaches for single-pol synthetic aperture radar (SAR) imagery try to ensure a constant false-alarm rate (CFAR). A high performance ship detector relies on two key components:an accurate estimation to a sea surface distribution and a fine designed CFAR algorithm. First, a novel nonparametric sea surface distribution estimation method is developed based on n-order Bézier curve. To estimate the sea surface distribution using n-order Bézier curve, an explicit analytical solution is derived based on a least square optimization, and the optimal selection also is presented to two essential parameters, the order n of Bézier curve and the number m of sample points. Next, to validate the ship detection performance of the estimated sea surface distribution, the estimated sea surface distribution by n-order Bézier curve is combined with a cell averaging CFAR (CA-CFAR). To eliminate the possible interfering ship targets in background window, an improved automatic censoring method is applied. Comprehensive experiments prove that in terms of sea surface estimation performance, the proposed method is as good as a traditional nonparametric Parzen window kernel method, and in most cases, outperforms two widely used parametric methods, K and G0 models. In terms of computation speed, a major advantage of the proposed estimation method is the time consuming only depended on the number m of sample points while independent of imagery size, which makes it can achieve a significant speed improvement to the Parzen window kernel method, and in some cases, it is even faster than two parametric methods. In terms of ship detection performance, the experiments show that the ship detector which constructed by the proposed sea surface distribution model and the given CA-CFAR algorithm has wide adaptability to different SAR sensors, resolutions and sea surface homogeneities and obtains a leading performance on the test dataset.
-
Key words:
- Bé /
- zier curve /
- nonparametric method /
- ship detection /
- sea surface distribution /
- synthetic aperture radar
-
An Wentao,Xie Chunhua,Yuan Xinzhe.2014.An improved iterative censoring scheme for CFAR ship detection with SAR imagery.IEEE Transactions on Geoscience and Remote Sensing,52(8):4585-4595 Bishop C M.1995.Neural Networks for Pattern Recognition.New York:Oxford University Press Brusch S,Lehner S,Fritz T,et al.2011.Ship surveillance with Ter-raSAR-X.IEEE Transactions on Geoscience and Remote Sensing, 49(3):1092-1103 Crisp D J.2004.The state-of-the-art in ship detection in synthetic aperture radar imagery (No.DSTO-RR-0272).Salisbury:De-fence Science and Technology Organisation Salisbury (Australia)Info Sciences Lab Cui Yi,Zhou Guangyi,Yang Jian,et al.2011.On the iterative censoring for target detection in SAR images.IEEE Geoscience and Remote Sensing Letters,8(4):641-645 El-Darymli K,McGuire P,Power D,et al.2013.Target detection in synthetic aperture radar imagery:a state-of-the-art survey.Bézier curves to improve the estimation precision;(2) Cui et al.Journal of Applied Remote Sensing,7(1):071598 LANG Haitao et al.Acta Oceanol.Sin.,2016,Vol.35,No.9,P.117-125 Farouki R T.2012.The Bernstein polynomial basis:a centennial retrospective.Computer Aided Geometric Design,29(6):379-419 Frery A C,Müller H J,Yanasse C D C F,et al.1997.A model for extremely heterogeneous clutter.IEEE Transactions on Geoscience and Remote Sensing,35(3):648-659 Gao Gui.2010.Statistical modeling of SAR images:A survey.Sensors, 10(1):775-795 Gao Gui.2011.A parzen-window-kernel-based CFAR algorithm for ship detection in SAR images.IEEE Geoscience and Remote Sensing Letters,8(3):557-561 Gao Gui,Liu Li,Zhao Lingjun,et al.2009.An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images.IEEE Transactions on Geoscience and Remote Sensing,47(6):1685-1697 Ji Yonggang,Zhang Jie,Meng Junmin,et al.2010.A new CFAR ship target detection method in SAR imagery.Acta Oceanologica Sinica,29(1):12-16 Krylov V A,Moser G,Serpico S B,et al.2011.Enhanced dictionary-based SAR amplitude distribution estimation and its validation with very high-resolution data.IEEE Geoscience and Remote Sensing Letters,8(1):148-152 Krylov V A,Moser G,Serpico S B,et al.2013.On the method of logarithmic cumulants for parametric probability density function estimation.IEEE Transactions on Image Processing,22(10):3791-3806 Kullback S.1987.The kullback-leibler distance.The American Statistician, 41(4):340-341 Kuruo.lu E E,Zerubia J.2004.Modeling SAR images with a generalization of the Rayleigh distribution.IEEE Transactions on Image Processing,13(4):527-533 Lang Haitao,Zhang Jie,Zhang Ting,et al.2014.Hierarchical ship detection and recognition with high-resolution polarimetric synthetic aperture radar imagery.Journal of Applied Remote Sensing, 8(1):083623 Li Hengchao,Hong Wen,Wu Yirong,et al.2010.An efficient and flexible statistical model based on generalized Gamma distribution for amplitude SAR images.IEEE Transactions on Geoscience and Remote Sensing,48(6):2711-2722 Li Hengchao,Hong Wen,Wu Yirong,et al.2011.On the empirical-statistical modeling of SAR images with generalized gamma distribution.IEEE Journal of Selected Topics in Signal Processing, 5(3):386-397 Mantero P,Moser G,Serpico S B.2005.Partially supervised classification of remote sensing images through SVM-based probability density estimation.IEEE Transactions on Geoscience and Remote Sensing,43(3):559-570 Moser G,Zerubia J,Serpico S B.2006a.Dictionary-based stochastic expectation-maximization for SAR amplitude probability density function estimation.IEEE Transactions on Geoscience and Remote Sensing,44(1):188-200 Moser G,Zerubia J,Serpico S B.2006b.SAR amplitude probability density function estimation based on a generalized Gaussian model.IEEE Transactions on Image Processing,15(6):1429-1442 Nicolas J M.2002.Introduction aux Statistiques de deuxième espèce:applications des Logs-moments et des Logs-cumulants àl'analyse des lois d'images radar.Traitement du Signal (in French), 19(3):139-167 Oliver C J.1993.Optimum texture estimators for SAR clutter.Journal of Physics D:Applied Physics,26(11):1824-1835 Oliver C,Quegan S.2004.Understanding Synthetic Aperture Radar Images.Raleigh,NC:SciTech Publishing Parzen E.1962.On estimation of a probability density function and mode.The Annals of Mathematical Statistics,33(3):1065-1076 Stuart A,Keith J.2008.Kendall's Advanced Theory of Statistics.6th ed.New York:Wiley Wang Changcheng,Liao Mingsheng,Li Xiaofeng.2008.Ship detection in SAR image based on the alpha-stable distribution.Sensors, 8(8):4948-4960 Zhao Di,Lang Haitao,Zhang Xi,et al.2015a.Sea clutter modeling by statistical majority consistency for ship detection in SAR imagery.IEEE International Geoscience and Remote Sensing Symposium (IGARSS).Milan:IEEE,3695-3698 Zhao Di,Meng Junmin,Zhang Xi,et al.2015b.Sea clutter statistics based on similarity fitting of classical models.Haiyang Xuebao(in Chinese),37(5):112-120
点击查看大图
计量
- 文章访问数: 1024
- HTML全文浏览量: 44
- PDF下载量: 403
- 被引次数: 0