基于Wishart距离和超像素的极化SAR图像车辆检测

doi:10.12305/j.issn.1001-506X.2021.10.08

摘要/Abstract

摘要：

针对极化合成孔径雷达(synthetic aperture radar, SAR)在城市区域复杂地物条件下的密集车辆目标检测问题, 提出了一种结合超像素分割和Wishart分类器的非监督目标检测方法。首先，根据不同地物的极化散射特征检测出建筑物。然后，利用不包含建筑物的Wishart分类器和超像素分割获得目标的形态信息。接着，利用包含建筑物的Wishart分类器获得目标中心点。最后，通过区域生长对二者进行信息融合并完成目标检测任务。基于X波段的机载极化SAR数据表明, 所提算法不仅可以对密集目标进行区分和定位, 并且目标形态保持完整; 相比于传统方法, 目标检测与虚警鉴别性能得到较大提升。

关键词: 车辆检测, 超像素分割, 极化合成孔径雷达, Wishart分类

Abstract:

Aiming at the problem of dense vehicle target detection in polarimetric synthetic aperture radar (SAR) from urban areas under complex scenarios, an unsupervised target detection method that combines the superpixel segmentation and the Wishart classifier is proposed. Firstly, the buildings are detected based on the different polarimetric scattering characteristics of ground objects. Then, the morphological information of the target is obtained by the Wishart classifier without buildings and the superpixel segmentation. After that, the center points of the target are obtained by the Wishart classifier with buildings. Finally, the region growing procedure is used to fuse the information obtained by above-mentio ned classifiers to complete the target detection task. Experimental results implemented on X-band airborne polarimetric SAR data illustrate that the proposed method can not only distinguish and locate dense targets, but also keep the shape of targets. Compared with traditional methods, the performance of target detection and false alarm discrimiantion is improved.

Key words: vehicle detection, superpixel segmentation, polarimetric synthetic aperture radar(SAR), Wishart classifier

中图分类号:

TP751.1

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.

Xiaokang DAI, Junjun YIN, Jian YANG. Vehicle detection based on Wishart distance and superpixel in polarimetric SAR image[J]. Systems Engineering and Electronics, 2021, 43(10): 2766-2774.

图/表 21

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

图17

图18

图19

图20

图21

参考文献 30

1	WANG T, YIN J J, YANG J, et al. Image gradient-based fast superpixel segmentation algorithm for PolSAR images[C]//Proc. of the 6th Asia-Pacific Conference on Synthetic Aperture Radar, 2019.
2	LIN H P, BAO J L, YIN J J, et al. Superpixel segmentation with boundary constraints for polarimetric SAR images[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2018: 6195-6198.
3	BAO J L, YIN J J, YANG J. Superpixel-based segmentation for multi-temporal PolSAR images[C]//Prof. of the Electromagnetics Research Symposium-Fall, 2017: 654-658.
4	LIN H P , YUAN F , XING C , et al. An edge attention-based geodesic distance for PolSAR image superpixel segmentation[J]. Electronics Letters, 2020, 56 (10): 510- 512. doi: 10.1049/el.2019.3890
5	QUAN S N , XIANG D L , WANG W , et al. Scattering feature-driven superpixel segmentation for polarimetric SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14, 2173- 2183. doi: 10.1109/JSTARS.2021.3053161
6	PIRRONE D , DE S , BHATTACHARYA A , et al. An Unsupervised approach to change detection in Built-up areas by multitemporal PolSAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 17 (11): 1914- 1918.
7	ZHAO J Q , CHANG Y L , YANG J , et al. A novel change detection method based on statistical distribution characteristics using multi-temporal PolSAR data[J]. Sensors, 2020, 20 (5): 1508. doi: 10.3390/s20051508
8	LIU F , TANG X , ZHANG X R , et al. Large-scope PolSAR image change detection based on looking-around-and-into mode[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 59 (1): 363- 378.
9	AKBARI V , ANFINSEN S N , DOULGERIS A P , et al. Polarimetric SAR change detection with the complex hotelling-lawley trace statistic[J]. IEEE Trans.on Geoscience and Remote Sensing, 2016, 54 (7): 3953- 3966. doi: 10.1109/TGRS.2016.2532320
10	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. doi: 10.3969/j.issn.1001-506X.2019.10.09
	HUANG C X , YIN J J , YANG J . Polarimetric SAR change detection with l1-norm principal component analysis[J]. Systems Engineering and Electronics, 2019, 41 (10): 2214- 2220. doi: 10.3969/j.issn.1001-506X.2019.10.09
11	LIU X Y, YIN J J, ZHANG J H, et al. Land cover classification for polsar images based on mixture models and MRF[C]//Proc. of the IEEE International Geoscience and Remote Sensing Symposium, 2020: 1711-1714.
12	YIN J J , LIU X Y , YANG J , et al. PolSAR image classification based on statistical distribution and MRF[J]. Remote Sensing, 2020, 12 (6): 1027. doi: 10.3390/rs12061027
13	LIU X Y, YIN J J, WANG T. Local competitive wishart classifier for polarimetric sar images[C]//Prof. of the IEEE International Geoscience and Remote Sensing Symposium, 2019: 2591-2594.
14	DUAN Y , CHEN N , CHEN Y B . A novel PolSAR image classification method based on optimal polarimetric features and contextual information[J]. Canadian Journal of Remote Sensing, 2019, 45 (6): 795- 813. doi: 10.1080/07038992.2019.1697222
15	ZOU B , XU X F , ZHANG L M . Object-based classification of polsar images based on spatial and semantic features[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 609- 619. doi: 10.1109/JSTARS.2020.2968966
16	GU M F , LIU H W , WANG Y , et al. PolSAR target detection via reflection symmetry and a wishart classifier[J]. IEEE Access, 2020, 8, 103317- 103326. doi: 10.1109/ACCESS.2020.2999472
17	HE J L , WANG Y H , LIU H W , et al. A novel automatic PolSAR ship detection method based on superpixel-level local information measurement[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (3): 384- 388. doi: 10.1109/LGRS.2017.2789204
18	WANG Y H , LIU H W . PolSAR ship detection based on superpixel-level scattering mechanism distribution features[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12 (8): 1780- 1784. doi: 10.1109/LGRS.2015.2425873
19	NEUMANN C, BRANDFAßM. Polarimetric target detection on SAR images[C]//Proc. of the 20th International Radar Symposium, 2019.
20	高军山, 陈杭, 林慧平, 等. 高分辨力极化SAR图像城市区域车辆目标检测[J]. 太赫兹科学与电子信息学报, 2018, 16 (4): 603- 608.
	GAO J S , CHEN H , LIN H P , et al. Vehicle detection over urban areas in high resolution polarimetric SAR images[J]. Terahertz Science and Electronic Information Technology, 2018, 16 (4): 603- 608.
21	ZHANG Z , ZOU C , HAN P , et al. A runway detection method based on classification using optimized polarimetric features and hog features for PolSAR images[J]. IEEE Access, 2020, 8, 49160- 49168. doi: 10.1109/ACCESS.2020.2979737
22	刘春, 包君梁, 杨健, 等. 基于混合Wishart分布MRF分割的极化SAR图像海岸线检测[J]. 系统工程与电子技术, 2020, 42 (3): 568- 574.
	LIU C , BAO J L , YANG J , et al. Coastline detection in polarimetric SAR images using Markov random field segmentation based on mixture Wishart distribution[J]. Systems Engineering and Electronics, 2020, 42 (3): 568- 574.
23	LIU C , XIAO Y , YANG J . A coastline detection method in polarimetric SAR images mixing the region-based and edge-based active contour models[J]. IEEE Trans.on Geoscience and Remote Sensing, 2017, 55 (7): 3735- 3747. doi: 10.1109/TGRS.2017.2679112
24	NOVAK L M , BURL M C . Optimal speckle reduction in polari-metric SAR imagery[J]. IEEE Trans.on Aerospace and Electronic Systems, 1990, 26 (2): 293- 305. doi: 10.1109/7.53442
25	LIU Z F, PING Q W, HE P K. An improved algorithm for the detection of vehicle group targets in high-resolution SAR images[C]//Proc. of the 3th International Conference on Microwave and Millimeter Wave Technology, 2002: 572-575.
26	LEE J S , GRUNES M R . Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution[J]. International Journal of Remote Sensing, 1994, 15 (11): 2299- 2311. doi: 10.1080/01431169408954244
27	张嘉峰, 朱博, 张鹏, 等. Wishart分布情形下极化SAR图像目标CFAR检测解析方法[J]. 电子学报, 2018, 46 (2): 433- 439. doi: 10.3969/j.issn.0372-2112.2018.02.024
	ZHANG J F , ZHU B , ZHANG P , et al. Polarimetric SAR imagery target CFAR detection analytical algorithm with Wishart distribution[J]. Acta Electronica Sinica, 2018, 46 (2): 433- 439. doi: 10.3969/j.issn.0372-2112.2018.02.024
28	AN W T , CUI Y , YANG J , et al. Fast alternatives to H/alpha for Polarimetric SAR[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7 (2): 343- 347. doi: 10.1109/LGRS.2009.2035135
29	韩萍, 周波, 卢斌, 等. 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. doi: 10.3969/j.issn.1001-506X.2020.10.11
	HAN P , ZHOU B , LU B , et al. 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. doi: 10.3969/j.issn.1001-506X.2020.10.11
30	LEVINSHTEIN A , STERE A , KUTULAKOS K N , et al. TurboPixels: fast superpixels using geometric flows[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2009, 31 (12): 2290- 2297. doi: 10.1109/TPAMI.2009.96

[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]	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.
[3]	邵宁远, 邹焕新, 陈诚, 李美霖, 秦先祥. 面向变化检测的SAR图像超像素协同分割算法[J]. 系统工程与电子技术, 2019, 41(7): 1496-1503.
[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]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	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.
[13]	李增辉, 常雯, 杨健. 基于超分辨极化SAR图像的舰船检测算法[J]. 系统工程与电子技术, 2015, 37(8): 1773-1777.
[14]	韩萍, 丛润民, 张在吉. 基于极化状态提取的极化SAR图像变化检测算法[J]. 系统工程与电子技术, 2015, 37(7): 1526-1530.
[15]	刘修国, 陈奇, 陈启浩, 徐乔. 综合多特征的高分辨率极化SAR图像分割[J]. 系统工程与电子技术, 2015, 37(3): 553-559.