基于多特征加权的SAR影像舰船检测优化方法

doi:10.11959/j.issn.1000-436x.2020013

通信学报 ›› 2020, Vol. 41 ›› Issue (3): 91-101.doi: 10.11959/j.issn.1000-436x.2020013

基于多特征加权的SAR影像舰船检测优化方法

赵泉华¹,王肖¹,李玉¹,王光辉²

¹ 辽宁工程技术大学测绘与地理科学学院，辽宁阜新 123000
² 国家测绘地理信息局卫星测绘应用中心，北京 100048

修回日期:2019-12-14 出版日期:2020-03-25 发布日期:2020-03-31
作者简介:赵泉华（1978- ），女，河北承德人，博士，辽宁工程技术大学教授、博士生导师，主要研究方向为随机几何、空间统计学、模糊集理论等在遥感图像建模、解译及海洋环境遥感中的应用|王肖（1996- ），女，辽宁阜新人，辽宁工程技术大学硕士生，主要研究方向为遥感图像处理|李玉（1963- ），男，吉林长春人，博士，辽宁工程技术大学教授、博士生导师，主要研究方向为遥感图像处理|王光辉（1982- ），男，河南商丘人，国家测绘地理信息局高级工程师，主要研究方向为遥感图像处理
基金资助:
辽宁省教育厅科学技术研究基金资助项目(LJ2019JL001)

Ship detection optimization method in SAR imagery based on multi-feature weighting

Quanhua ZHAO¹,Xiao WANG¹,Yu LI¹,Guanghui WANG²

¹ School of Geomatics,Liaoning Technical University,Fuxin 123000,China
² Satellite Surveying and Mapping Application Center,NASG,Beijing 100048,China

Revised:2019-12-14 Online:2020-03-25 Published:2020-03-31
Supported by:
The Project of Science and Technology Research of Education Department of Liaoning Province(LJ2019JL001)

摘要/Abstract

摘要：

针对虚警目标较多的复杂场景中，传统舰船检测算法检测结果精度偏低的问题，提出了一种基于多特征加权的SAR影像舰船检测优化方法。首先，采用标记分水岭算法对SAR幅度影像进行去陆操作；其次，利用基于对数正态分布的恒虚警率算法，得到去陆 SAR 影像的候选目标；再次，提取候选目标的长宽比、舰船面积和对比度3个特征；最后，提出变异系数法对3个特征进行权重分配，并结合候选目标的归一化特征矢量计算其特征置信度，再确定最佳置信度，去除候选目标中的虚警目标，优化舰船检测结果。为了验证所提方法，选取不同复杂场景的高分三号SAR影像进行舰船检测实验。实验结果表明，所提方法具有可行性和有效性。

关键词: 合成孔径雷达, 舰船检测, 对数正态分布, 恒虚警率, 权重分配

Abstract:

Aiming at the problem that the accuracy of traditional ship detection algorithms is not satisfying in complex scene with many false alarm targets,a ship detection optimization method in SAR imagery based on multi-feature weighting was proposed.Firstly,the marker-based watershed algorithm was employed to remove land from SAR amplitude image.Then,the CFAR algorithm based on log-normal distribution was used to obtain candidate targets from no land image.Furthermore,the length to width ratio,the ship area and the contrast ratio of the candidate targets were extracted.Finally,a variance coefficient method was proposed to distribute the weight of the three features,and the confidence levels were calculated by combining the normalized feature vectors of the candidate targets with the feature weight.By determining the best confidence level,false alarm targets among the candidate targets were removed to optimize ship detection results.In order to verify the proposed method,experiments were carried on with the GF-3 SAR images of different complex scenes.The experimental results show that the proposed method is feasible and effective.

Key words: synthetic aperture radar, ship detection, log-normal distribution, constant false alarm rate, weight allocation

中图分类号:

TP237

赵泉华,王肖,李玉,王光辉. 基于多特征加权的SAR影像舰船检测优化方法[J]. 通信学报, 2020, 41(3): 91-101.

Quanhua ZHAO,Xiao WANG,Yu LI,Guanghui WANG. Ship detection optimization method in SAR imagery based on multi-feature weighting[J]. Journal on Communications, 2020, 41(3): 91-101.

图/表 12

图1

图2

图3

表1

图4

图5

图6

表2

图7

表3

图8

表4

参考文献 23

[1]	蒋李兵, 王壮, 雷琳 ,等. 基于模型迭代匹配的单幅高分辨SAR图像遮挡建筑物高度估计方法[J]. 通信学报, 2013,34(3): 68-75.
	JIANG L B , WANG Z , LEI L ,et al. Occluded building height estimation from single HR SAR image based on an iterative model matching technique[J]. Journal on Communications, 2013,34(3): 68-75.
[2]	ARMANDO M , MARIA S F , IRENA H ,et al. Ship detection with spectral analysis of synthetic aperture radar:a comparison of new and well-known algorithms[J]. Remote Sensing, 2015,7(5): 5416-5439.
[3]	MOREIRA A , PRATS-IRAOLA P , YOUNIS M ,et al. A tutorial on synthetic aperture radar[J]. IEEE Geoscience and Remote Sensing Magazine, 2013,1(1): 6-43.
[4]	LENG X G , JI K F , YANG K ,et al. A bilateral CFAR algorithm for ship detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2015,12(7): 1536-1540.
[5]	杨国铮, 禹晶, 肖创柏 ,等. 基于形态字典学习的复杂背景SAR图像舰船尾迹检测[J]. 自动化学报, 2017,43(10): 1713-1725.
	YANG G Z , YU J , XIAO C B ,et al. Ship wake detection in SAR images with complex background using morphological dictionary learning[J]. Acta Automatica Sinica, 2017,43(10): 1713-1725.
[6]	魏钜杰, 李平湘, 杨杰 ,等. 利用全极化SAR数据去方位向模糊的舰船目标检测方法[J]. 测绘学报, 2013,42(4): 530-539.
	WEI J J , LI P X , YANG J ,et al. Removing the effects of azimuth ambiguities on ships detection based on polarimetric SAR data[J]. Acta Geodaetica et Cartographica Sinica, 2013,42(4): 530-539.
[7]	陈德元, 涂国防 . 一种基于小波变换的 SAR 图像船舰检测的新算法[J]. 电子与信息学报, 2007,29(4): 855-858.
	CHEN D Y , TU G F . A new algorithm of ship targets detection in SAR images using wavelet transform[J]. Journal of Electronics and Information Technology, 2007,29(4): 855-858.
[8]	HOU B , CHEN X Z , JIAO L C . Multilayer CFAR detection of ship targets in very high resolution SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2015,12(4): 811-815.
[9]	WANG Y H , LIU H W . A hierarchical ship detection scheme for high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing,2012,50(10), 2012,50 (4): 811-815.
[10]	赵明波, 何峻, 付强 . SAR图像CFAR检测的快速算法综述[J]. 自动化学报, 2012,38(12): 1885-1895.
	ZHAO M B , HE J , FU Q . Survey on fast CFAR detection algorithms for SAR image targets[J]. Acta Automatica Sinica, 2012,38(12): 1885-1895.
[11]	高贵 . SAR图像目标ROI自动获取技术研究[D]. 长沙:国防科学技术大学, 2007.
	GAO G . The research on automatic acquirement of target’s ROI from SAR imagery[D]. Changsha:National University of Defense Technology, 2007.
[12]	NOVAK L M , HALVERSEN S D , OWIRKA G ,et al. Effects of polarization and resolution on SAR ATR[J]. IEEE Transactions on Aerospace and Electronic Systems, 1997,33(1): 102-116.
[13]	种劲松, 朱敏慧 . SAR图像局部窗口K-分布目标检测算法[J]. 电子与信息学报, 2003(9): 1276-1280.
	ZHONG J S , ZHU M H . K-distribution target detection in local window of SAR image[J]. Journal of Electronics and information Technology, 2003(9): 1276-1280.
[14]	邢相薇, 陈振林, 邹焕新 ,等. 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(8): 256-259.
	XING X W , CHEN Z L , ZOU H X ,et al. A fast algorithm based on two-stage CFAR for detecting ships in SAR images[J]. Journal of Signal Processing, 2009,25(8): 256-259.
[15]	高贵, 蒋咏梅, 张琦 ,等. 基于多特征联合的高分辨率SAR图像机动目标快速获取[J]. 电子学报, 2006(9): 1663-1667.
	GAO G , JIANG Y M , ZHANG Q ,et al. Fast acquirement of vehicle targets from high-resolution SAR images based on combining multi-feature[J]. Acta Electronica Sinica, 2006(9): 1663-1667.
[16]	杨高波, 张兆杨, 余圣发 ,等. 一种基于小波分解和分水岭变换的视频对象自动分割算法[J]. 通信学报, 2005,26(3): 7-13.
	YANG G B , ZHANG Z Y , YU S F ,et al. Automatic video object extraction algorithm based on wavelet and watershed[J]. Journal on Communications, 2005,26(3): 7-13.
[17]	郭昱杉, 刘庆生, 刘高焕 ,等. 基于标记控制分水岭分割方法的高分辨率遥感影像单木树冠提取[J]. 地球信息科学学报, 2016,18(9): 1259-1266.
	GUO Y S , LIU Q S , LIU G H ,et al. Individual tree crown extraction of high resolution image based on marker-controlled watershed segmentation method[J]. Journal of Geo-Information Science, 2016,18(9): 1259-1266.
[18]	AI J Q , QI X Y , YU W D ,et al. A new CFAR ship detection algorithm based on 2-D joint log-normal distribution in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2010,7(4): 806-810.
[19]	COVER T M , THOMAS J A . Elements of information theory[M]. New Jersey: John Wiley ＆ SonsPress, 1991.
[20]	甄勇, 刘伟, 陈建宏 ,等. 高分辨率SAR图像舰船目标几何结构特征提取[J]. 信号处理, 2016,32(4): 424-429.
	ZHEN Y , LIU W , CHEN J H ,et al. Geometric structure feature extraction of ship target in high-resolution SAR image[J]. Journal of Signal Processing, 2016,32(4): 424-429.
[21]	程鹏飞, 闫浩文, 韩振辉 . 一个求解多边形最小面积外接矩形的算法[J]. 工程图学学报, 2008,29(1): 122-126.
	CHENG P F , YAN H W , HAN Z H . An algorithm for computing the minimum area bounding rectangle of an arbitrary polygon[J]. Journal of Engineering Graphics, 2008,29(1): 122-126.
[22]	赵微, 林健, 王树芳 ,等. 变异系数法评价人类活动对地下水环境的影响[J]. 环境科学, 2013,34(4): 1277-1283.
	ZHAO W , LIN J , WANG S F ,et al. Influence of human activities on groundwater environment based on coefficient variation method[J]. Environmental Science, 2013,34(4): 1277-1283.
[23]	种劲松 . 合成孔径图像舰船目标检测方法与应用研究[D]. 长沙:中国科学院研究生院, 2002.
	ZHONG J S . A study on the algorithm of ship target detection in SAR imagery and its applications[D]. Changsha:Graduate University of Chinese Academy of Sciences, 2002.

影像	成像模式	分辨率/m	入射角
影像1	FS1	2.81	40.6°
影像2	FS1	2.81	42.8°

序号	长宽比	舰船面积/像素	对比度	归一化特征矢量	置信度
a₁	4.47	234	0.98	0.66,0.09,0.18]	29.88%
a₂	2.12	570	1.24	0,0.93,0.44]	51.04%
a₃	3.57	523	1.53[	0.36,0.81,0.73]	64.31%
a₄	4.97	469	1.10	0.82,0.67,0.30]	63.44%
b₁	2.29	56	0.78	0,0,0]	0
b₂	1.10	620	1.33	0,0,0.53]	12.19%
b₃	1.28	649	1.12	0,0,0.32]	7.36%
b₄	1.89	6396	1.45	0,0,0.65]	14.95%

算法	时间/s
最佳熵双阈值算法	0.47
双参数CFAR算法	232.03
本文算法	256.98

影像	检测算法	真实舰船数量	正确检测数	漏检数	虚警数	错检数	检测率	品质因子
	最佳熵双阈值算法		52	3	0	3	94.5%	89.7%
实验影像1	双参数CFAR算法	55	53	2	4	6	96.4%	86.9%
	本文算法		55	0	1	1	100.0%	98.2%
	最佳熵双阈值算法		17	0	9	9	100.0%	65.4%
实验影像2	双参数CFAR算法	17	17	0	7	7	100.0%	70.8%
	本文算法		17	0	0	0	100.0%	100.0%
	最佳熵双阈值算法		136	11	431	442	92.5%	23.1%
实验影像3	双参数CFAR算法	147	87	60	167	227	59.2%	23.3%
	本文算法		140	7	8	15	95.2%	86.4%

基于多特征加权的SAR影像舰船检测优化方法

Ship detection optimization method in SAR imagery based on multi-feature weighting

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 23

相关文章 6

Metrics

推荐阅读 0

[1]	郭宝锋,尚朝轩,王昕,马俊涛,董健. 空间目标双基地ISAR越多普勒单元徒动校正算法[J]. 通信学报, 2014, 35(9): 197-206.
[2]	齐兆群，景晓军，游思晴，孙海斌. 基于不变矩的微动目标二维平流层ISAR成像算法[J]. 通信学报, 2013, 34(8): 9-75.
[3]	齐兆群,景晓军,游思晴,孙海斌. 基于不变矩的微动目标二维平流层ISAR成像算法[J]. 通信学报, 2013, 34(8): 70-75.
[4]	孙凤莲,张群,罗迎,顾福飞,王国正. 基于压缩感知的稀疏孔径认知ISAR成像方法[J]. 通信学报, 2012, 33(Z2): 262-269.
[5]	王广学,黄晓涛,周智敏. UWB SAR叶簇隐蔽目标差值变化检测中杂波分布建模分析与应用[J]. 通信学报, 2012, 33(2): 76-81.
[6]	孙造宇,梁甸农,路兴强,张永胜. 星载InSAR系统干涉信号模拟方法[J]. 通信学报, 2006, 27(8): 57-61.