环境特征与散射特性融合的PolSAR飞机目标检测

doi:10.3969/j.issn.1001-506X.2020.10.11

摘要/Abstract

摘要：

针对复杂场景下极化合成孔径雷达(polarimetric synthetic aperture radar, PolSAR)图像飞机目标检测问题,提出了一种融合目标环境特征与散射特性的PolSAR飞机目标检测方法。首先，利用极化白化滤波(polarimetric whitening filter, PWF)图提取疑似飞机目标,将疑似飞机目标转换成超像素得到混合图像。然后，经极化分解与分类构造一个新的环境特征,并与散射特性融合得到飞机目标检测特征,通过阈值判别检测出飞机目标。最后，使用AIRSAR和UAVSAR系统采集的实测数据进行实验,并与其他检测方法进行对比。结果表明,所提方法产生的虚警和漏警较已有方法有所改善,检测结果更好。

关键词: 极化合成孔径雷达, 飞机目标检测, 极化白化滤波, 环境特征, 散射特性

Abstract:

In order to solve the problem of aircraft target detection by polarimetric synthetic aperture radar (PolSAR) image in complex scene. A PolSAR aircraft target detection method based on the fusion of target environmental feature and scattering characteristics is proposed. Firstly, the polarimetric whitening filter (PWF) map is used to extract the suspected aircraft target which is converted into super-pixels to obtain a mixed image. Then, after polarimetric decomposition and classification, a new environmental feature is constructed and fused with the scattering characteristics to obtain the aircraft target detection feature. Threshold discrimination is used for aircraft target detection. Finally, the testing data collected by the AIRSAR and UAVSAR systems is used for experiments, and compared with other detection methods. The experimental results indicate that the false alarms and missing alarms generated by the proposed method are reduced and the detection results are much better compared with the existing methods.

Key words: polarimetric synthetic aperture radar (PolSAR), aircraft target detection, polarimetric whitening filter (PWF), environmental feature, scattering characteristics

中图分类号:

TP753

韩萍, 周波, 卢斌, 韩宾宾. 环境特征与散射特性融合的PolSAR飞机目标检测[J]. 系统工程与电子技术, 2020, 42(10): 2231-2238.

Ping HAN, Bo ZHOU, Bin LU, Binbin HAN. Aircraft target detection of PolSAR based on the fusion of environmental feature and scattering characteristics[J]. Systems Engineering and Electronics, 2020, 42(10): 2231-2238.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

表2

参考文献 19

1	JACKSON C R, RAIS H. Detection of aircraft crash sites from space using fully polarimetric SIR-C SAR imagery for search and rescue applications[C]//Proc.of the SPIE Conference on Automatic Target Recognition IX, 1999: 213-220.
2	HAN P, GE P, WU R B. Crashed plane detection based on the fusion of CFAR detection and polarimetric decomposition[C]//Proc.of the IEEE CIE International Conference on Radar, 2011: 744-747.
3	HAN P, ZHANG X S, GE P. Crashed airplane detection based on feature fusion in PolSAR image[C]//Proc.of the 11th IEEE International Conference on Signal Processing, 2012: 2003-2006.
4	LUKOWSKI T I , CHARBONNEAU F J . Synthetic aperture radar and search and rescue: detection of crashed aircraft using ima-gery and interferometric methods[J]. Canadian Journal of Remote Sensing, 2002, 28 (6): 770- 781. doi: 10.5589/m02-070
5	HAN P, HAN B B, SHI Q Y, et al. Aircraft detection based on eigen decomposition and scattering similarity for PolSAR image[C]//Proc.of the 37th IEEE/AIAA Digital Avionics Systems Conference, 2018.
6	卢晓光, 周波, 韩萍, 等. 多特征分类的PolSAR图像飞机目标检测[J]. 信号处理, 2019, 35 (4): 563- 573.
	LU X G , ZHOU B , HAN P , et al. Aircraft detection based on multi-feature classification for PolSAR image[J]. Journal of Signal Processing, 2019, 35 (4): 563- 573.
7	韩萍, 陈丽丽. 基于极化交叉熵和Yamaguchi分解的飞机目标检测方法[J]. 信号处理, 2017, 33 (3): 389- 396.
	HAN P , CHEN L L . Airplane detection algorithm of polarimetric SAR image based on polarimetric cross entropy and Yamaguchi decomposition[J]. Journal of Signal Processing, 2017, 33 (3): 389- 396.
8	韩萍, 宋厅华. 区域筛选与多级特征判别相结合的PolSAR图像飞机目标检测[J]. 中国图象图形学报, 2019, 24 (7): 1197- 1206.
	HAN P , SONG T H . Aircraft target detection of PolSAR image combined with regional screening and multi-feature discriminant[J]. Journal of Image and Graphics, 2019, 24 (7): 1197- 1206.
9	LOPES A , SERY F . Optimal speckle reduction for the product model in multilook polarimetric SAR imagery and the Wishart distribution[J]. IEEE Trans.on Geoscience and Remote Sens-ing, 1997, 35 (3): 632- 647. doi: 10.1109/36.581979
10	AN W T , CUI Y , YANG J . Fast alternatives to H/α for polari-metric SAR[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7 (2): 343- 347. doi: 10.1109/LGRS.2009.2035135
11	范庆辉, 慕建君, 项德良, 等. 基于非平稳性和极化相干系数比的PolSAR图像建筑物检测[J]. 电子与信息学报, 2016, 38 (12): 3238- 3244.
	FAN Q H , MU J J , XIANG D L , et al. Built-up area detection from PolSAR images based on nonstationarity and polarization coherency coefficient ratio[J]. Journal of Electronics & Information Technology, 2016, 38 (12): 3238- 3244.
12	韩萍, 韩宾宾. 基于典型散射差异指数的PolSAR图像Lee滤波[J]. 系统工程与电子技术, 2018, 40 (2): 287- 294.
	HAN P , HAN B B . Lee filter of PolSAR image based on typical scattering difference index[J]. Systems Engineering and Electronics, 2018, 40 (2): 287- 294.
13	AN W T , XIE C H , YUAN X Z , et al. Four-component decomposition of polarimetric SAR images with deorientation[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8 (6): 1090- 1094. doi: 10.1109/LGRS.2011.2157078
14	ZHOU G Y , CUI Y , CHEN Y L , et al. Linear feature detection in polarimetric SAR images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2011, 49 (4): 1453- 1463. doi: 10.1109/TGRS.2010.2081373
15	LEE J S , GRUNES M R , POTTIER E , et al. Unsupervised terrain classification preserving polarimetric scattering characteristics[J]. IEEE Trans.on Geoscience and Remote Sensing, 2004, 42 (4): 722- 731. doi: 10.1109/TGRS.2003.819883
16	WANG S , LIU K , PEI J J , et al. Unsupervised classification of fully polarimetric SAR images based on scattering power entropy and copolarized ratio[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10 (3): 622- 626. doi: 10.1109/LGRS.2012.2216249
17	HOU B , KOU H D , JIAO L C . Classification of polarimetric SAR images using multilayer autoencoders and superpixels[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9 (7): 3072- 3081. doi: 10.1109/JSTARS.2016.2553104
18	LIU B , HU H , WANG H Y , et al. Superpixel-based classification with an adaptive number of classes for polarimetric SAR images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2013, 51 (2): 907- 924. doi: 10.1109/TGRS.2012.2203358
19	何伟, 邢孟道. 基于密度峰值搜索的全极化SAR图像分类[J]. 系统工程与电子技术, 2016, 38 (1): 60- 63.
	HE W , XING M D . Classification method for PolSAR images based on find of density peak[J]. Systems Engineering and Electronics, 2016, 38 (1): 60- 63.

样本标号	飞机		建筑物		跑道		海水		森林
样本标号	坐标	\|γ\|	坐标	\|γ\|	坐标	\|γ\|	坐标	\|γ\|	坐标	\|γ\|
1	(31, 157)	0.918 2	(20, 121)	0.731 6	(73, 266)	0.515 8	(141, 18)	0.604 0	(78, 45)	0.027 3
2	(37, 190)	0.925 9	(107, 203)	0.992 4	(89, 201)	0.306 8	(165, 54)	0.540 5	(103, 81)	0.018 9
3	(38, 195)	0.936 0	(27, 117)	0.725 6	(110, 143)	0.295 1	(190, 9)	0.324 2	(187, 202)	0.088 1
4	(38, 199)	0.936 2	(119, 281)	0.808 9	(43, 192)	0.663 4	(151, 6)	0.512 8	(199, 224)	0.089 9
5	(96, 188)	0.927 5	(31, 274)	0.859 1	(36, 69)	0.412 2	(189, 23)	0.462 5	(16, 321)	0.102 3

场景名称	场景大小	数据采集系统	方法	N_rt	N_dt	N_fa	N_ma	FoM
Half-Moon-bay区域	401×830	AIRSAR	本文	2	2	1	0	0.667
			文献[7]	2	2	22	0	0.083
			文献[8]	2	2	7	0	0.222
Kahului airport区域	203×346	UAVSAR	本文	5	5	3	0	0.625
			文献[7]	5	5	16	0	0.238
			文献[8]	5	4	4	1	0.445
Hilo airport区域	323×645	UAVSAR	本文	8	7	1	1	0.778
			文献[7]	8	4	27	4	0.114
			文献[8]	8	6	13	2	0.286
Kaneohe Bay区域1	389×352	UAVSAR	本文	28	24	4	4	0.750
			文献[7]	28	10	72	18	0.100
			文献[8]	28	17	26	11	0.315
Kaneohe Bay区域2	501×701	UAVSAR	本文	28	24	5	4	0.727
			文献[7]	28	10	134	18	0.062
			文献[8]	28	17	55	11	0.205
Kona airport区域	501×413	UAVSAR	本文	15	13	14	2	0.448
			文献[7]	15	6	17	9	0.188
			文献[8]	15	13	6	2	0.619

[1]	牛朝阳, 王建涛, 胡涛, 刘伟, 李润生. 极化合成孔径雷达有源干扰的干信比方程[J]. 系统工程与电子技术, 2021, 43(12): 3542-3551.
[2]	管灵, 朱晨曦, 董纯柱, 殷红成. 基于模式/区域分解的无人机集群电磁特性快速分析[J]. 系统工程与电子技术, 2021, 43(10): 2697-2705.
[3]	代晓康, 殷君君, 杨健. 基于Wishart距离和超像素的极化SAR图像车辆检测[J]. 系统工程与电子技术, 2021, 43(10): 2766-2774.
[4]	韩萍, 贾锟, 卢晓光, 韩宾宾. PolSAR图像的改进非局部均值滤波算法[J]. 系统工程与电子技术, 2019, 41(5): 992-999.
[5]	郭杰, 殷红成, 满良. 无源散射单元电磁散射特性可控方法综述[J]. 系统工程与电子技术, 2019, 41(4): 716-723.
[6]	李建周, 刘祥威, 范超群, 刘露, 齐玉涛. 多自由度飞行目标动态建模及其散射特性分析[J]. 系统工程与电子技术, 2019, 41(11): 2401-2407.
[7]	黄晨霞, 殷君君, 杨健. 基于l1范数主成分分析的极化SAR图像变化检测[J]. 系统工程与电子技术, 2019, 41(10): 2214-2220.
[8]	王剑, 王英华, 刘宏伟, 何敬鲁. 基于深度卷积神经网络的PolSAR图像变化检测方法[J]. 系统工程与电子技术, 2018, 40(7): 1457-1464.
[9]	韩萍, 韩宾宾. 基于典型散射差异指数的PolSAR图像Lee滤波 [J]. 系统工程与电子技术, 2018, 40(2): 287-294.
[10]	张海瀛, 李真芳, 解金卫. 车载全极化InSAR系统通道误差校正[J]. 系统工程与电子技术, 2017, 39(2): 298-303.
[11]	韩萍, 常玲, 程争, 石庆研. 基于h/q分解和贝叶斯迭代分类的跑道检测算法[J]. 系统工程与电子技术, 2016, 38(9): 2048-2054.
[12]	赵晓彤, 郭琨毅, 盛新庆, 屈泉酉. 前向雷达目标回波成分与特性分析[J]. 系统工程与电子技术, 2016, 38(11): 2523-2529.
[13]	何伟, 邢孟道. 基于密度峰值搜索的全极化SAR图像分类[J]. 系统工程与电子技术, 2016, 38(1): 60-63.
[14]	杨帅, 陈启浩, 刘修国, 陈奇. 面向高分辨率极化SAR四分量分解的相干矩阵自适应估计[J]. 系统工程与电子技术, 2016, 38(1): 53-59.
[15]	谭洪, 仇晓兰, 洪峻. 原始数据压缩对全极化SAR极化信息的影响[J]. 系统工程与电子技术, 2015, 37(9): 2029-2034.