基于马尔科夫判别谱聚类的极化SAR图像分类方法

张向荣 于心源 唐旭 侯彪 焦李成

张向荣, 于心源, 唐旭, 等. 基于马尔科夫判别谱聚类的极化SAR图像分类方法[J]. 雷达学报, 2019, 8(4): 425–435. doi: 10.12000/JR19059
引用本文: 张向荣, 于心源, 唐旭, 等. 基于马尔科夫判别谱聚类的极化SAR图像分类方法[J]. 雷达学报, 2019, 8(4): 425–435. doi: 10.12000/JR19059
ZHANG Xiangrong, YU Xinyuan, TANG Xu, et al. PolSAR image classification method based on Markov discriminant spectral clustering[J]. Journal of Radars, 2019, 8(4): 425–435. doi: 10.12000/JR19059
Citation: ZHANG Xiangrong, YU Xinyuan, TANG Xu, et al. PolSAR image classification method based on Markov discriminant spectral clustering[J]. Journal of Radars, 2019, 8(4): 425–435. doi: 10.12000/JR19059

基于马尔科夫判别谱聚类的极化SAR图像分类方法

doi: 10.12000/JR19059
基金项目: 国家自然科学基金(61772400),陕西省重点研发计划(2019ZDLGY03-08)
详细信息
    作者简介:

    张向荣(1978–),女,西安电子科技大学人工智能学院,教授/博导,IEEE高级会员,IEEE GRSS西安分会副主席。主要从事遥感影像智能解译、机器学习、模式识别相关方向研究。E-mail: xrzhang@mail.xidian.edu.cn

    于心源(1993–),女,西安电子科技大学研究生。研究领域为极化SAR图像处理、机器学习等

    唐旭:唐 旭(1985–),男,西安电子科技大学人工智能学院讲师,IEEE会员。主要从事遥感影像内容解译方向的研究

    侯彪:侯 彪(1974–),男,西安电子科技大学人工智能学院,教授/博导,IEEE会员。从事人工智能、类脑计算、遥感脑、图像和视频分析、智能教育等研究

    焦李成(1959–),男,西安电子科技大学人工智能学院,教授/博导,IEEE Fellow, IEEE GRSS西安分会主席,IEEE Transactions on Geoscience and Remote Sensing副主编。主要从事人工智能相关领域的研究

    通讯作者:

    张向荣 xrzhang@mail.xidian.edu.cn

  • 中图分类号: TN958

PolSAR Image Classification Method Based on Markov Discriminant Spectral Clustering

Funds: The National Natural Science Foundation of China (61772400), The Key Research and Development Plans of Shaanxi Province (2019ZDLGY03-08)
More Information
  • 摘要: 该文针对现有的谱聚类方法用于极化SAR图像分类时精度较低的问题,提出一种基于马尔科夫的判别谱聚类方法(MDSC),具有低秩和稀疏分解的特点。该方法首先恢复一个真实的低秩概率转移矩阵,将其作为标准马尔科夫谱聚类方法的输入,以减少噪声对分类结果的影响;然后在目标函数中引入判别信息,使极化SAR图像的数据信息能够得到更加充分地利用;最后采用增广拉格朗日乘子法来解决低秩和概率单纯形约束下的目标函数优化问题。在荷兰小农田、德国、西安和荷兰大农田4个不同数据集上的实验证明,该方法具有较好的准确率,且参数敏感性较低,表现出了良好的分类性能。

     

  • 图  1  真实的概率转移矩阵构造概图

    Figure  1.  Real probability transfer matrix construction profile

    图  2  本文算法框架图

    Figure  2.  Algorithm frame diagram

    图  3  荷兰Flevoland地区农田小图的伪彩图、类标图以及不同算法的分类结果图

    Figure  3.  Pseudo-color map, class diagram and classification results of different algorithms for farmland maps in the Flevoland region of the Netherlands

    图  4  德国Oberpfaffenhofen地区数据的伪彩图、类标图以及不同算法的分类结果图

    Figure  4.  Pseudo-color map, class diagram and data classification results of different algorithms in the Oberpfaffenhofen region of Germany

    图  5  西安地区数据的伪彩图、类标图以及不同算法的分类结果图

    Figure  5.  Pseudo-color map, class diagram and data classification results of different algorithms in Xi’an area

    图  6  荷兰 Flevoland 地区大农田数据的伪彩图、类标图以及不同算法的分类结果图

    Figure  6.  Pseudo-color map, class diagram and classification results of different algorithms for large farmland data in the Flevoland region of the Netherlands

    图  7  荷兰小农田中不同$\lambda $$\beta $下的分类结果图

    Figure  7.  Classification results of different $\lambda $ and $\beta $ below in small Dutch farmland

    图  10  不同正则项参数$\xi $的分类结果图

    Figure  10.  Classification results of different regular item parameter $\xi $

    图  8  德国地区中不同$\lambda $$\beta $下的分类结果

    Figure  8.  Classification results for different $\lambda $ and $\beta $ below in the German region

    图  9  西安地区中不同$\lambda $$\beta $下的分类结果图

    Figure  9.  Classification results of different $\lambda $ and $\beta $ subordinates in Xi’an area

    表  1  4种算法对Flevoland小农田图的分类结果

    Table  1.   Classification results of four algorithms for Flevoland small farmland map

    裸土土豆甜菜大麦豌豆小麦OAAAKappa
    Co-Reg0.88600.94520.75510.79060.82620.89600.84000.84980.8775
    MMC0.91800.95800.72420.96230.87560.69940.87080.83960.9005
    SR-MO0.90340.90490.88450.95610.83620.95540.91300.90670.9331
    本文算法0.90480.90880.88340.96040.89200.93820.92430.91460.9418
    下载: 导出CSV

    表  2  4种算法对德国Oberpfaffenhofen地区的分类结果

    Table  2.   Classification results of four algorithms for the Oberpfaffenhofen region of Germany

    Co-RegMMCSR-MO本文算法
    农田0.61110.60180.68590.7016
    居民区0.60720.65210.73360.7389
    林地0.81620.79930.90550.9108
    道路0.53110.56810.60490.6418
    其他0.87910.87890.86730.8814
    OA0.73630.74710.78220.7974
    AA0.68890.70000.75940.7749
    Kappa0.61700.63480.69200.7205
    下载: 导出CSV

    表  3  4种算法对西安地区的分类结果

    Table  3.   Classification results of four algorithms for Xi’an area

    Co-RegMMCSR-MO本文算法
    河流0.93720.88760.91890.8890
    城区0.73000.66220.81280.8550
    植被0.68760.80520.80060.8555
    OA0.74000.76700.82270.8503
    AA0.72590.75840.81360.8436
    Kappa0.73410.77100.80710.8471
    下载: 导出CSV

    表  4  4种算法对荷兰 Flevoland 地区大农田图的分类结果

    Table  4.   Classification results of four algorithms for large farmland maps in the Flevoland region of the Netherlands

    Co-RegMMCSR-MO本文算法
    蚕豆0.74590.89420.96140.9584
    油菜籽0.13930.71940.70940.8337
    裸地0.20560.96160.95410.9583
    土豆0.24790.89120.87960.9086
    甜菜0.10790.94810.96560.9515
    小麦20.24270.62510.85250.7941
    豌豆0.79320.95170.88870.9571
    小麦30.54120.92310.91800.9300
    苜蓿0.95410.89400.83910.9284
    大麦0.92260.63110.96600.8524
    小麦0.11580.84580.86600.8796
    草地0.39440.64590.74700.8773
    森林0.40410.88330.83290.9122
    水域0.54030.97570.90350.9620
    建筑物0.59540.77610.58650.7912
    OA0.42040.84410.85010.8923
    AA0.41650.83980.86970.9043
    Kappa0.42690.84090.84410.9136
    下载: 导出CSV
  • [1] 邹焕新, 罗天成, 张月, 等. 基于组合条件随机场的极化SAR图像监督地物分类[J]. 雷达学报, 2017, 6(5): 541–553. doi: 10.12000/JR16109

    ZOU Huanxin, LUO Tiancheng, ZHANG Yue, et al. Combined conditional random fields model for supervised PolSAR images classification[J]. Journal of Radars, 2017, 6(5): 541–553. doi: 10.12000/JR16109
    [2] FREEMAN A and 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. doi: 10.1109/36.673687
    [3] BUONO A, NUNZIATA F, MIGLIACCIO M, et al. Classification of the Yellow River delta area using fully polarimetric SAR measurements[J]. International Journal of Remote Sensing, 2017, 38(23): 6714–6734. doi: 10.1080/01431161.2017.1363437
    [4] JOULIN A, BACH F, and PONCE J. Discriminative clustering for image co-segmentation[C]. Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 1943–1950.
    [5] HARALICK R M, SHANMUGAM K, and DINSTEIN I. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610–621. doi: 10.1109/TSMC.1973.4309314
    [6] RATHA D, BHATTACHARYA A, and FRERY A C. Unsupervised classification of PolSAR data using a scattering similarity measure derived from a geodesic distance[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(1): 151–155. doi: 10.1109/LGRS.2017.2778749
    [7] AHMED N and CAMPBELL M. Variational Bayesian learning of probabilistic discriminative models with latent softmax variables[J]. IEEE Transactions on Signal Processing, 2011, 59(7): 3143–3153. doi: 10.1109/TSP.2011.2144587
    [8] LIN Zhouchen, CHEN Minming, and MA Ya. The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices[J]. Eprint Arxiv, 2010(9): 26.
    [9] XIA Rongkai, PAN Yan, DU Lei, et al. Robust multi-view spectral clustering via low-rank and sparse decomposition[C]. Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, Québec City, 2014: 2149–2155.
    [10] CAI Jianfeng, CANDÈS E J, and SHEN Zuowei. A singular value thresholding algorithm for matrix completion[J]. SIAM Journal on Optimization, 2010, 20(4): 1956–1982. doi: 10.1137/080738970
    [11] ZHU Ciyou, BYRD R H, LU Peihuang, et al. Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization[J]. ACM Transactions on Mathematical Software, 1997, 23(4): 550–560. doi: 10.1145/279232.279236
    [12] KUMAR Y, MULLER U, BEN J, et al. spectral clustering MIT Press[C]. 24th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2010.
    [13] MATSUGU M, MORI K, ISHII M, et al. Convolutional spiking neural network model for robust face detection[C]. Proceedings of the 9th International Conference on Neural Information Processing, Singapore, Singapore, 2002: 660–664.
  • 加载中
图(10) / 表(4)
计量
  • 文章访问数:  1322
  • HTML全文浏览量:  417
  • PDF下载量:  196
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-06-01
  • 修回日期:  2019-07-22
  • 网络出版日期:  2019-07-25
  • 刊出日期:  2019-08-28

目录

    /

    返回文章
    返回