多特征分类的PolSAR图像飞机目标检测
|
摘要
针对目前有关极化合成孔径雷达(Polarimetric Synthetic Aperture Radar, PolSAR)的飞机目标检测算法虚警较多、自适应性较差的问题,给出一种复杂大场景中PolSAR图像多特征分类的飞机目标检测方法。该方法分为线下分类器训练和飞机目标检测两部分。使用Filter特征选择结合穷举法筛选出分类性能高的飞机极化特征训练SVM(Support Vector Machine, SVM)分类器;利用异化散射功率提取疑似飞机目标,进一步提取多个极化特征送入SVM分类获得检测结果。利用UAVSAR系统采集的多幅实测数据进行实验,并与现有的PolSAR图像飞机目标检测算法进行对比,结果表明该方法能够有效检测出飞机目标,并且虚警和漏警较少,方法自适应性有所提高。
Aiming at the problem of high false alarm and poor flexibility in aircraft detection by PolSAR image, this paper presents a new aircraft detection algorithm for PolSAR image with large complex scenes. The performance of the detection process consists of SVM classifier training and detection of aircraft target. In the procedure of SVM training, multiple optimized polarization features of the aircrafts are selected through the combination of Filter feature selection and exhaustive method to train the SVM classifier. In the detection process, suspected aircraft targets are selected from the large PolSAR image by threshold method with dissimilation scattering power, then multiple polarization features extracted from the suspected aircraft targets will be input to the SVM classifier to obtain the detection result. The multiple testing data collected by UAVSAR system and the comparison with the existing algorithm of PolSAR image indicate that the method presented in this paper could effectively detect aircraft targets with less false and missed alarm as well as improved flexibility.
Aiming at the problem of high false alarm and poor flexibility in aircraft detection by PolSAR image, this paper presents a new aircraft detection algorithm for PolSAR image with large complex scenes. The performance of the detection process consists of SVM classifier training and detection of aircraft target. In the procedure of SVM training, multiple optimized polarization features of the aircrafts are selected through the combination of Filter feature selection and exhaustive method to train the SVM classifier. In the detection process, suspected aircraft targets are selected from the large PolSAR image by threshold method with dissimilation scattering power, then multiple polarization features extracted from the suspected aircraft targets will be input to the SVM classifier to obtain the detection result. The multiple testing data collected by UAVSAR system and the comparison with the existing algorithm of PolSAR image indicate that the method presented in this paper could effectively detect aircraft targets with less false and missed alarm as well as improved flexibility.
引文
[1] Novak L M,Burl M C.Optimal Speckle Reduction in PolSAR Imagery and Its Effect on Target Detection[C]//SPIE in the proceeding of Millimeter Wave and Synthetic Aperture Radar,Orlando,USA,1989,110:84-115.
[2] Yang J,Yamaguchi Y,Boerner W M,et al.Numerical Methods for Solving the Optimal Problem of Contrast Enhancement[J].IEEE Trans Geosci Remote Sens,2000,38(2):965-971.
[3] Novak L M,Burl M C.Studies of Target Detection Algorithms that Use Polarimetric Radar Data[J].IEEE Transactions on Aerospace and Electronic Systems,1989,25(2):150-165.
[4] 高伟,殷君君,杨健.基于Riemann核Fisher准则的极化SAR图像人造目标检测[J].清华大学学报:自然科学版,2016,56(9):920-924.Gao Wei,Yin Junjun,Yang Jian.Man-made Target Detection in Polarimetric SAR Images Using the Riemannian Kernel Fisher criterion[J].Journal of Tsinghua University:Science and Technology,2016,56(9):920-924.(in Chinese)
[5] 韩萍,徐建飒.复杂场景下的极化SAR图像机场跑道检测[J].信号处理,2013,29(9):1220-1226.Han Ping,Xu Jiansa.Runways Detection in Complex Scenes of Polarimetric Synthetic Aperture Radar Image[J].Journal of Signal Processing,2013,29(9):1220-1226.(in Chinese)
[6] 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.Zhang Jiafeng,Zhu Bo,Zhang Peng,et al.Polarimetric SAR Imagery Target CFAR Detection Analytical Algorithm with Wishart Distribution[J].Acta Electronica Sinica,2018,46(2):433- 439.(in Chinese)
[7] 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.Chengdu,2011:744-747.
[8] 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.Beijing,2012:2003-2006.
[9] 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 Ping,Chen Lili.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.(in Chinese)
[10] Han P,Han B B,Shi Q Y,et al.Aircraft Detection Based on Eigen Decomposition and Scattering Similarity for PolSAR Image[C]//2018 IEEE/AIAA 37th Digital Avionics Systems Conference(DASC),London,United Kingdom,2018:1- 6.
[11] 折小强,雷斌.一种基于极化熵的极化SAR海岸线提取方法[J].国外电子测量技术,2017,36(8):76- 82.She Xiaoqiang,Lei Bin.New Polarimetric Entropy Based Coastline Extraction Method for PolSAR Images[J].Foreign Electronic Measurement Technology,2017,36(8):76- 82.(in Chinese)
[12] Yamaguchi Y,Moriyama T,Ishido M,et al.Four Component Scattering Model for Polarimetric SAR Image Decomposition[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(8):1699-1706.
[13] Freeman A,Durden S L.A Three-Component Scattering Model for Polarimetric SAR Data[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):963-973.
[14] 匡纲要,陈强,蒋咏梅.极化合成孔径雷达基础理论及其应用[M].长沙:国防科技大学出版社,2011:136-137.Kuang Gangyao,Chen Qiang,Jiang Yongmei.Polarimetric Synthetic Aperture Radar Basic Principles and its Applications[M].Changsha:Publishing House of National University of Defense Technology,2011:136-137.(in Chinese)
[15] An W T,Zhang W J,Yang J,et al.Similarity between Two Targets and its Application to Polarimetric Target Detection for Sea Area[C]//Progress in Electromagnetics Research Symposium.USA:Cambridge,2008:515-520.
[16] Xi Y Y,Zhang X,Lai Q,et al.A New PolSAR Ship Detection Metric Fused by Polarimetric Similarity and the Third Eigenvalue of the Coherency Matrix[C]//Geoscience and Remote Sensing Symposium.IEEE,2016:112-115.
[17] 王娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005(12):72-75.Wang Juan,Ci Linlin,Yao Kangze.A Survey of Feature Selection[J].Computer Engineering & Science,2005(12):72-75.(in Chinese)
[18] 姚旭,王晓丹,张玉玺,等.特征选择方法综述[J].控制与决策,2012,27(2):161-166.Yao Xu,Wang Xiaodan,Zhang Yuxi,et al.Summary of Feature Selection Algorithms[J].Control and Decision,2012,27(2):161-166.(in Chinese)
[19] 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,2018,33(1):119-127.Xiong Wei,Xu Yongli,Yao Libo,et al.A New Ship Target Detection Algorithm Based on SVM in High Resolution SAR Images[J].Remote Sensing Technology and Application,2018,33(1):119-127.(in Chinese)
[20] 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(2):287-294.Han Ping,Han Binbin.Lee filter of PolSAR Image Based on Typical Scattering Difference Index[J].Systems Engineering and Electronics,2018(2):287-294.(in Chinese)
[21] 安文韬.基于极化SAR的目标极化分解与散射特征提取研究[D].北京:清华大学,2010.An Wentao.The Polarimetric Decomposition and Scattering Characteristic Extraction of Polarimetric SAR[D].Beijing:Tsinghua University,2010.(in Chinese)
[22] 李仲森,鲍狄埃.极化雷达成像基础与应用[M].北京:电子工业出版社,2013:179-181.Jong-Sen Lee,Eric Pottier.Polarimetric Radar Imaging:From Basics to Applications[M].Beijing:Publishing House of Electronics Industry,2013:179-181.(in Chinese)
[2] Yang J,Yamaguchi Y,Boerner W M,et al.Numerical Methods for Solving the Optimal Problem of Contrast Enhancement[J].IEEE Trans Geosci Remote Sens,2000,38(2):965-971.
[3] Novak L M,Burl M C.Studies of Target Detection Algorithms that Use Polarimetric Radar Data[J].IEEE Transactions on Aerospace and Electronic Systems,1989,25(2):150-165.
[4] 高伟,殷君君,杨健.基于Riemann核Fisher准则的极化SAR图像人造目标检测[J].清华大学学报:自然科学版,2016,56(9):920-924.Gao Wei,Yin Junjun,Yang Jian.Man-made Target Detection in Polarimetric SAR Images Using the Riemannian Kernel Fisher criterion[J].Journal of Tsinghua University:Science and Technology,2016,56(9):920-924.(in Chinese)
[5] 韩萍,徐建飒.复杂场景下的极化SAR图像机场跑道检测[J].信号处理,2013,29(9):1220-1226.Han Ping,Xu Jiansa.Runways Detection in Complex Scenes of Polarimetric Synthetic Aperture Radar Image[J].Journal of Signal Processing,2013,29(9):1220-1226.(in Chinese)
[6] 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.Zhang Jiafeng,Zhu Bo,Zhang Peng,et al.Polarimetric SAR Imagery Target CFAR Detection Analytical Algorithm with Wishart Distribution[J].Acta Electronica Sinica,2018,46(2):433- 439.(in Chinese)
[7] 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.Chengdu,2011:744-747.
[8] 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.Beijing,2012:2003-2006.
[9] 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 Ping,Chen Lili.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.(in Chinese)
[10] Han P,Han B B,Shi Q Y,et al.Aircraft Detection Based on Eigen Decomposition and Scattering Similarity for PolSAR Image[C]//2018 IEEE/AIAA 37th Digital Avionics Systems Conference(DASC),London,United Kingdom,2018:1- 6.
[11] 折小强,雷斌.一种基于极化熵的极化SAR海岸线提取方法[J].国外电子测量技术,2017,36(8):76- 82.She Xiaoqiang,Lei Bin.New Polarimetric Entropy Based Coastline Extraction Method for PolSAR Images[J].Foreign Electronic Measurement Technology,2017,36(8):76- 82.(in Chinese)
[12] Yamaguchi Y,Moriyama T,Ishido M,et al.Four Component Scattering Model for Polarimetric SAR Image Decomposition[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(8):1699-1706.
[13] Freeman A,Durden S L.A Three-Component Scattering Model for Polarimetric SAR Data[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):963-973.
[14] 匡纲要,陈强,蒋咏梅.极化合成孔径雷达基础理论及其应用[M].长沙:国防科技大学出版社,2011:136-137.Kuang Gangyao,Chen Qiang,Jiang Yongmei.Polarimetric Synthetic Aperture Radar Basic Principles and its Applications[M].Changsha:Publishing House of National University of Defense Technology,2011:136-137.(in Chinese)
[15] An W T,Zhang W J,Yang J,et al.Similarity between Two Targets and its Application to Polarimetric Target Detection for Sea Area[C]//Progress in Electromagnetics Research Symposium.USA:Cambridge,2008:515-520.
[16] Xi Y Y,Zhang X,Lai Q,et al.A New PolSAR Ship Detection Metric Fused by Polarimetric Similarity and the Third Eigenvalue of the Coherency Matrix[C]//Geoscience and Remote Sensing Symposium.IEEE,2016:112-115.
[17] 王娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005(12):72-75.Wang Juan,Ci Linlin,Yao Kangze.A Survey of Feature Selection[J].Computer Engineering & Science,2005(12):72-75.(in Chinese)
[18] 姚旭,王晓丹,张玉玺,等.特征选择方法综述[J].控制与决策,2012,27(2):161-166.Yao Xu,Wang Xiaodan,Zhang Yuxi,et al.Summary of Feature Selection Algorithms[J].Control and Decision,2012,27(2):161-166.(in Chinese)
[19] 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,2018,33(1):119-127.Xiong Wei,Xu Yongli,Yao Libo,et al.A New Ship Target Detection Algorithm Based on SVM in High Resolution SAR Images[J].Remote Sensing Technology and Application,2018,33(1):119-127.(in Chinese)
[20] 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(2):287-294.Han Ping,Han Binbin.Lee filter of PolSAR Image Based on Typical Scattering Difference Index[J].Systems Engineering and Electronics,2018(2):287-294.(in Chinese)
[21] 安文韬.基于极化SAR的目标极化分解与散射特征提取研究[D].北京:清华大学,2010.An Wentao.The Polarimetric Decomposition and Scattering Characteristic Extraction of Polarimetric SAR[D].Beijing:Tsinghua University,2010.(in Chinese)
[22] 李仲森,鲍狄埃.极化雷达成像基础与应用[M].北京:电子工业出版社,2013:179-181.Jong-Sen Lee,Eric Pottier.Polarimetric Radar Imaging:From Basics to Applications[M].Beijing:Publishing House of Electronics Industry,2013:179-181.(in Chinese)