基于累积量随机学习算法的高分辨率SAR图像舰船检测方法研究
|
摘要
基于SAR图像的舰船目标检测是海洋遥感应用的重要内容,恒虚警率(CFAR)是应用最为广泛的SAR图像舰船检测算法之一。由于CFAR算法的性能主要依赖于对海杂波概率密度的准确估计,本文提出一种基于累积量随机学习的海杂波概率密度估计方法,并采用两级CFAR级联的方法提高检测效率,通过对像素点聚类解决了高分辨率SAR图像舰船区域不连通的问题。实验结果表明,累积量随机学习算法能够更精确地估计海杂波概率密度,相比经典方法,本文提出的检测方法性能较好且检测效率较高。
Ship target detection based on SAR image is an important part of marine remote sensing application. Constant false alarm rate( CFAR) is one of the most widely used ship detection algorithms of SAR imagery. Since the performance of CFAR algorithm mainly depends on the accurate estimation of the probability density of sea clutter,this paper proposes a probability density estimation method of sea clutter based on a nonparametric method-Stochastic Learning of the Cumulative( SLC). Besides,the two-stage CFAR is used to improve the detection efficiency. The disconnection problem of ships in high resolution SAR images is solved by pixel clustering. The experimental results show that the SLC describes the probability density of sea clutter more accurately and the proposed method outperformed the traditional methods with lower false alarm rate and higher detection efficiency.
Ship target detection based on SAR image is an important part of marine remote sensing application. Constant false alarm rate( CFAR) is one of the most widely used ship detection algorithms of SAR imagery. Since the performance of CFAR algorithm mainly depends on the accurate estimation of the probability density of sea clutter,this paper proposes a probability density estimation method of sea clutter based on a nonparametric method-Stochastic Learning of the Cumulative( SLC). Besides,the two-stage CFAR is used to improve the detection efficiency. The disconnection problem of ships in high resolution SAR images is solved by pixel clustering. The experimental results show that the SLC describes the probability density of sea clutter more accurately and the proposed method outperformed the traditional methods with lower false alarm rate and higher detection efficiency.
引文
[1]P.W.Vachon.Ship Detection by the RADARSAT SAR:validation of detection model predictions[J].Canadian Journal of Remote Sensing,1997,23(1):48-59.
[2]种劲松,朱敏慧.SAR图像舰船及尾迹检测研究综述[J].电子学报,2003,31(9):1356-1360.
[3]艾加秋,齐向阳.一种基于局部K-分布的新的SAR图像舰船检测算法[J].中国科学院研究生院学报.2010,27(1):36-42.
[4]唐沐恩,林挺强,文贡坚.遥感图像中舰船检测方法综述[J].计算机应用研究,2011,28(1):29-36.
[5]C.C.Wakerman.Automatic ship detection of ships in RADARSAT SAR imagery[J].Canadian Journal of Remote Sensing,2001,27(5):371-378.
[6]MARIVI T,CARLOS L.A novel algorithm for ship detection in SAR imagery based on the wavelet transform[J].IEEE Geoscience and Remote Sensing Letter,2005,2(2):201-205
[7]Ouchi K,Tamaki S,Yaguchi H,et al.Ship detection based on coherence images derived from cross correlation of multilook SAR images[J].IEEE Geoscience&Remote Sensing Letters,2004,1(3):184-187.
[8]Xing X,Ji K,Zou H,et al.Feature selection and weighted SVM classifier-based ship detection in Pol SAR imagery[J].International Journal of Remote Sensing,2013,34(22):7925-7944.
[9]熊伟,徐永力,姚力波,等.基于SVM的高分辨率SAR图像舰船目标检测算法[J].遥感技术与应用,2018(1).
[10]邢相薇.HRWSSAR图像舰船目标监视关键技术研究[D].国防科学技术大学,2014.
[11]K.Eldhuset.An automatic ship and ship wake detection system for spaceborne SAR images in Coastal Regions[J].IEEE Trans.on Geoscience and remote sensing,1996,34(4):1010-1019.
[12]M.Greco,F.Gini,A.Farina.Combined effect of phase and RGPO delay quantization on jamming signal spectrum[C].//2015 IEEE International Radar Conference.[S.I.]:IEEE Press,2005:37-42.
[13]邢相薇,陈振林,邹焕新.一种基于两级CFAR的SAR图像舰船目标快速检测算法[J].信号处理,2009,25(8A):256-259.
[14]Y.Cui,G.Y.Zhou,J.Yang,Y.Yamaguchi.On the iterative censoring for target detection in SAR images[J].IEEE Geoscicence and Remote Sensing Letters,2011,8(4):641-645.
[15]M.I.Malik,A.Amir.Density estimation and random variate generation using multilayer network[J].IEEETrans.on Neural Networks,2002,13(3):497-520.
[16]赵峰,张军英,刘敬,梁军利.基于非参数化概率密度估计的雷达目标识别[J].电子与信息学报,2008,30(7):1740-1743.
[17]H.N.Jenq,L.R.Shyh,L.Alan.Nonparametric multivariate density estimation:a comparative study[J].IEEE Trans.on Signal Processing,1994,42(10),2795-2810.
[18]C.T.Jun,S.David.Incremental kernel principal component analysis[J].IEEE Trans.on Image processing.2007,16(6):1661-1674.
[2]种劲松,朱敏慧.SAR图像舰船及尾迹检测研究综述[J].电子学报,2003,31(9):1356-1360.
[3]艾加秋,齐向阳.一种基于局部K-分布的新的SAR图像舰船检测算法[J].中国科学院研究生院学报.2010,27(1):36-42.
[4]唐沐恩,林挺强,文贡坚.遥感图像中舰船检测方法综述[J].计算机应用研究,2011,28(1):29-36.
[5]C.C.Wakerman.Automatic ship detection of ships in RADARSAT SAR imagery[J].Canadian Journal of Remote Sensing,2001,27(5):371-378.
[6]MARIVI T,CARLOS L.A novel algorithm for ship detection in SAR imagery based on the wavelet transform[J].IEEE Geoscience and Remote Sensing Letter,2005,2(2):201-205
[7]Ouchi K,Tamaki S,Yaguchi H,et al.Ship detection based on coherence images derived from cross correlation of multilook SAR images[J].IEEE Geoscience&Remote Sensing Letters,2004,1(3):184-187.
[8]Xing X,Ji K,Zou H,et al.Feature selection and weighted SVM classifier-based ship detection in Pol SAR imagery[J].International Journal of Remote Sensing,2013,34(22):7925-7944.
[9]熊伟,徐永力,姚力波,等.基于SVM的高分辨率SAR图像舰船目标检测算法[J].遥感技术与应用,2018(1).
[10]邢相薇.HRWSSAR图像舰船目标监视关键技术研究[D].国防科学技术大学,2014.
[11]K.Eldhuset.An automatic ship and ship wake detection system for spaceborne SAR images in Coastal Regions[J].IEEE Trans.on Geoscience and remote sensing,1996,34(4):1010-1019.
[12]M.Greco,F.Gini,A.Farina.Combined effect of phase and RGPO delay quantization on jamming signal spectrum[C].//2015 IEEE International Radar Conference.[S.I.]:IEEE Press,2005:37-42.
[13]邢相薇,陈振林,邹焕新.一种基于两级CFAR的SAR图像舰船目标快速检测算法[J].信号处理,2009,25(8A):256-259.
[14]Y.Cui,G.Y.Zhou,J.Yang,Y.Yamaguchi.On the iterative censoring for target detection in SAR images[J].IEEE Geoscicence and Remote Sensing Letters,2011,8(4):641-645.
[15]M.I.Malik,A.Amir.Density estimation and random variate generation using multilayer network[J].IEEETrans.on Neural Networks,2002,13(3):497-520.
[16]赵峰,张军英,刘敬,梁军利.基于非参数化概率密度估计的雷达目标识别[J].电子与信息学报,2008,30(7):1740-1743.
[17]H.N.Jenq,L.R.Shyh,L.Alan.Nonparametric multivariate density estimation:a comparative study[J].IEEE Trans.on Signal Processing,1994,42(10),2795-2810.
[18]C.T.Jun,S.David.Incremental kernel principal component analysis[J].IEEE Trans.on Image processing.2007,16(6):1661-1674.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |