基于加权合成核与三重Markov场的极化SAR图像分类方法

doi:10.3969/j.issn.0372-2112.2016.03.004

电子学报 ›› 2016, Vol. 44 ›› Issue (3): 520-526.DOI: 10.3969/j.issn.0372-2112.2016.03.004

基于加权合成核与三重Markov场的极化SAR图像分类方法

宋婉莹, 李明, 张鹏, 吴艳, 贾璐, 刘高峰

西安电子科技大学雷达信号处理国家重点实验室, 陕西西安 710071

收稿日期:2014-07-15 修回日期:2015-02-10 出版日期:2016-03-25
- 通讯作者:
- 李明
- 作者简介:
- 宋婉莹 女,1988年生于山东聊城.现为西安电子科技大学雷达信号处理国家重点实验室博士研究生.研究方向为极化SAR图像处理、多传感器信息融合等. E-mail:wanyingsong@hotmail.com;
- 基金资助:
- 国家自然科学基金 (No.61271297,No.61272281,No.61301284); 博士学科点科研专项基金 (No.20110203110001); 国家部委预研基金 (No.9140A07020913DZ01001,No.9140C010205140C01004)

A Classification Method of PolSAR Image Based on Weighted Composite Kernel and Triplet Markov Field

SONG Wan-ying, LI Ming, ZHANG Peng, WU Yan, JIA Lu, LIU Gao-feng

National Laboratory of Radar Signal Processing, Xidian University, Xi'an, Shaanxi 710071, China

Received:2014-07-15 Revised:2015-02-10 Online:2016-03-25 Published:2016-03-25
- Supported by:
- National Natural Science Foundation of China (No.61271297, No.61272281, No.61301284); Ph.D. Programs Foundation (No.20110203110001); Pre-research Fund of National Ministries and Commissions (No.9140A07020913DZ01001, No.9140C010205140C01004)

摘要/Abstract

摘要：

马尔可夫随机场(Markov Random Field,MRF)广泛用于处理遥感图像的分类问题,然而MRF在构建极化合成孔径雷达(Synthetic Aperture Radar,SAR)图像模型时未考虑其非平稳特性且对初始分类较为敏感,为此本文提出了一种基于加权合成核与三重马尔可夫随机场(Triplet Markov Field,TMF)的极化SAR图像分类方法.该方法依据训练样本在特征空间上的距离,提出了加权合成核函数权重系数的自适应确定方法以提高初始分类的精度和普适性;为充分考虑极化SAR图像的非平稳统计特性,利用TMF对极化SAR图像进行统计建模以实现贝叶斯分类.实验结果表明,与基于MRF的极化SAR图像分类方法相比,本文所提方法可获得更高的分类精度和更平滑的同质区域分类结果,而且本文方法能更好地保持图像边缘信息.

关键词: 极化合成孔径雷达, 图像分类, 加权合成核, 三重马尔可夫随机场, 支持向量机

Abstract:

Markov random field (MRF) is widely applied to remote sensing images classification.However,the MRF-based classification method does not take the nonstationarity properties of images into account when it models polarimetric synthetic aperture radar (PolSAR) images,and is sensitive to the initial classification.Therefore,this paper proposes a classification method of PolSAR image based on the weighted composite kernel and the triplet Markov field (TMF).Based on the distances between the features of training samples,we compute the kernel weights of the weighted composite kernel for improving the accuracy and popularity of the initial classification.Then,taking the nonstationarity properties of PolSAR images into consideration,the TMF is introduced to model the statistics of real PolSAR images to realize the Bayesian classification.Experiments indicate that the proposed method can obtain higher classification accuracy and smoother homogeneous areas than the MRF-based PolSAR image classification method.Moreover,the proposed method can get more accurate edge location.

Key words: polarimetric synthetic aperture radar (PolSAR), image classification, weight composite kernel, Triplet Markov Field (TMF), support vector machine (SVM)

中图分类号:

TN957.52

宋婉莹, 李明, 张鹏, 等. 基于加权合成核与三重Markov场的极化SAR图像分类方法[J]. 电子学报, 2016, 44(3): 520-526.

SONG Wan-ying, LI Ming, ZHANG Peng, et al. A Classification Method of PolSAR Image Based on Weighted Composite Kernel and Triplet Markov Field[J]. Acta Electronica Sinica, 2016, 44(3): 520-526.

参考文献

[1] LEE J S,POTTIER E.Polarimetric Radar Imaging from Basic to Application[M]. New York:CRC Press,2011.1-30,160-175.
[2] VAN ZYL J J,KIM Y.Synthetic Aperture Radar Polarimetry[M]. California:Jet Propulsion Laboratory,2011.85-155.
[3] 曹芳,洪文,吴一戎.基于Cloude_Pottier目标分解和聚合的层次聚类算法的全极化SAR数据的非监督分类算法研究[J]. 电子学报,2008,36(3):543-546. CAO Fang,HONG Wen,WU Yi-rong.An unsupervised classification for fully polarimetric SAR data using cloude-pottier decomposition and agglomerative hierarchical clustering algorithm[J]. Acta Electronica Sinica,2008,36(3):543-546.(in Chinese)
[4] CHEN Q,KUANG G Y,LI J,et al.Unsupervised land cover/land use classification using PolSAR imagery based on scattering similarity[J]. IEEE Transactions on Geoscience and Remote Sensing,2013,51(3):1817-1825.
[5] LIU B,HU H,WANG H Y,et al.Superpixel-based classification with an adaptive number of classes for polarimetric SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing,2013,51(2):907-924.
[6] LI S L.Markov Random Field Modeling in Image Analysis[M]. London:Springer-Verlag,2009.1-189.
[7] 张斌,杨然,谢兴.利用极化目标分解和WMRF的全极化SAR图像分类方法[J]. 武汉大学学报信息科学版,2011,36(3):297-301. ZHANG Bin,YANG Ran,XIE Xing.Classification of fully polarimetric SAR image based on polarimetric target decomposition and Wishart Markov random field[J]. Geomatics and Information Science of Wuhan University,2011,36(3):297-301.(in Chinese)
[8] WU Y,JI K,et al.Region-based classification of polarimetric SAR images using Wishart MRF[J]. IEEE Geoscience and Remote Sensing Letter,2008,5(4):668-672.
[9] WU Z C,OUYANG Q D.SVM- and MRF-based method for contextual classification of polarimetric SAR images[A]. International Geoscience and Remote Sensing Symposium[C]. Canada,Vancouver:IEEE Computer Society,2011.818-821.
[10] CAMPS-VALLS G,GÓMEZ-CHOVA L,et al.Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection[J]. IEEE Transactions on Geoscience and Remote Sensing,2008,46(6):1822-1835.
[11] BENBOUDJEMA D,PIECZYNSKI W.Unsupervised statistical segmentation of nonstationary images using triplet Markov fields[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(8):1367-1378.
[12] BENBOUDJEMA D,TUPIN F,et al.Unsupervised segmentation of SAR images using triplet Markov fields and Fisher noise distributions[A]. International Geoscience and Remote Sensing Symposium[C]. Barcelona,Spain:IEEE Computer Society,2007.3891-3894.
[13] LI G Q,WEN C Y,et al.Model-based online learning with kernels[J]. IEEE Transactions on Neural Networks and Learning Systems,2013,24(3):356-369.
[14] 刘高峰,李明,等.一种改进的极化SAR自适应非负特征值分解[J]. 电子与信息学报,2013,35(6):1449-1455. LIU Gao-feng,LI Ming,et al.An improved adaptive nonnegative eigenvalue decomposition for polarimetric synthetic aperture radar[J]. Journal of Electronics ＆ Information Technology,2013,35(6):1449-1455.(in Chinese)
[15] LIU G F,LI M,et al.Fast solution to nonnegative eigenvalue decomposition for polarimetric SAR[J]. IET Electronics Letters,2013,49(6):419-420.
[16] VAN ZYL J J.Unsupervised classification of scattering behavior using radar polarimetry data[J]. IEEE Transactions on Geoscience and Remote Sensing,1989,27(5):36-45.t al. Unsupervised land cover/land use classification using PolSAR imagery based on scattering similarity [J]. IEEE Transaction on Geoscience and Remote Sensing, 2013, 51(3): 1817-1825.
[5]Liu B, Hu H, Wang H Y, et al. Superpixel-based classification with an adaptive number of classes for polarimetric SAR images [J]. IEEE Transaction on Geoscience and Remote Sensing, 2013, 51(2): 907-924.
[6]Li S L. Markov Random Field Modeling in Image Analysis [M]. London: Springer-Verlag, 2009. 1-189.
[7]张斌, 杨然, 谢兴. 利用极化目标分解和WMRF的全极化SAR图像分类方法[J]. 武汉大学学报信息科学版, 2011, 36(3): 297-301.
[8]Wu Y, Ji K, Yu W, et al. Region-based classification of polarimetric SAR images using Wishart MRF [J]. IEEE Geoscience and Remote Sensing Letter, 2008, 5(4): 668-672.
[9]Wu Z C and Ouyang Q D. SVM- and MRF-based method for contextual classification of polarimetric SAR images [C]. IEEE IGARSS Proceedings, 2011. 818-821.
[10]Camps-Valls G, Gómez-Chova L, Mu?oz-Marí J, et al.. Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection [J]. IEEE Transaction on Geoscience and Remote Sensing, 2008, 46(6): 1822-1835.
[11]Benboudjema D and Pieczynski W. Unsupervised statistical segmentation of nonstationary images using triplet Markov fields [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(8): 1367–1378.
[12]Benboudjema D, Tupin F, Pieczynski W, et al. Unsupervised segmentation of SAR images using triplet Markov fields and Fisher noise distributions [C]. IEEE IGARSS Proceedings, 2007: 3891-3894.
[13]Li G Q, Wen C Y, and Li Z L. Model-based online learning with kernels [J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(3): 356-369.
[14] 刘高峰，李明，王亚军. 一种改进的极化SAR自适应非负特征值分解[J].电子与信息学报, 2013, 35(6): 1449-1455.
[15]Liu G F, Li M, Wang Y J, et al. Fast solution to nonnegative eigenvalue decomposition for polarimetric SAR [J]. IET Electronics Letters, 2013, 49(6): 419-420.
[16]Van Zyl J. Unsupervised classification of scattering behavior using radar polarimetry data. IEEE Trans. on Geoscience and Remote Sensing, 1989, 27(5): 36-45.

基于加权合成核与三重Markov场的极化SAR图像分类方法

A Classification Method of PolSAR Image Based on Weighted Composite Kernel and Triplet Markov Field

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[2]	王子为, 鲁继文, 周杰. 基于自适应梯度优化的二值神经网络[J]. 电子学报, 2023, 51(2): 257-266.
[3]	曹源, 宋迪, 胡小溪, 孙永奎. 基于改进时域多尺度散布熵与支持向量机的转辙机故障诊断[J]. 电子学报, 2023, 51(1): 117-127.
[4]	王雪松, 张翰林, 程玉虎. 基于自编码器和超图的半监督宽度学习系统[J]. 电子学报, 2022, 50(3): 533-539.
[5]	吴国庆, 王罗胜斌, 庞晨, 李永祯, 王雪松. 雷达极化域变焦角反组合体对抗方法：抗冲淡式干扰[J]. 电子学报, 2022, 50(12): 2969-2983.
[6]	赵旭东, 陶然, 李伟, 张蒙蒙. 高光谱图像分数域信息提取理论与方法进展[J]. 电子学报, 2022, 50(12): 2874-2883.
[7]	孙晨峰, 吕卫民, 戴洪德, 张浩晨. 一种基于TimeGAN和OCSVM的多元退化设备小子样数据增广方法[J]. 电子学报, 2022, 50(11): 2678-2687.
[8]	杨国为, 万鸣华, 赖志辉, 张凡龙, 黄伟强. 具有合适拒识机制的高正确识别率分类器设计[J]. 电子学报, 2021, 49(8): 1569-1576.
[9]	罗忠涛, 夏杭, 卢琨, 何子述. 超视距雷达中距离-多普勒图的瞬态干扰自动识别方法[J]. 电子学报, 2021, 49(7): 1279-1285.
[10]	钱忠胜, 俞情媛, 宋涛, 朱懿敏, 祝洁, 赵畅. 基于支持向量机回归模型的测试用例生成与重用[J]. 电子学报, 2021, 49(7): 1386-1391.
[11]	张芳鑫, 王法松, 李睿, 左婷. GSSK‑VLC系统中基于SVM的LED选择算法[J]. 电子学报, 2021, 49(7): 1400-1405.
[12]	刘芳, 韩笑. 基于小波变换和深度网络的着陆地貌图像分类[J]. 电子学报, 2021, 49(11): 2171-2176.
[13]	江泽涛, 秦嘉奇, 张少钦. 参数池化卷积神经网络图像分类方法[J]. 电子学报, 2020, 48(9): 1729-1734.
[14]	史聪伟, 赵杰煜, 陈瑜. 利用网格卷积特征的三维形变目标分类[J]. 电子学报, 2020, 48(4): 648-653.
[15]	张学军, 景鹏, 何涛, 孙知信. 基于变分模态分解的癫痫脑电信号分类方法[J]. 电子学报, 2020, 48(12): 2469-2475.