2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于边缘保持滤波的高光谱影像光谱-空间联合分类

张成坤 韩敏

张成坤, 韩敏. 基于边缘保持滤波的高光谱影像光谱-空间联合分类. 自动化学报, 2018, 44(2): 280-288. doi: 10.16383/j.aas.2018.c160704
引用本文: 张成坤, 韩敏. 基于边缘保持滤波的高光谱影像光谱-空间联合分类. 自动化学报, 2018, 44(2): 280-288. doi: 10.16383/j.aas.2018.c160704
ZHANG Cheng-Kun, HAN Min. Spectral-spatial Joint Classification of Hyperspectral Image with Edge-preserving Filtering. ACTA AUTOMATICA SINICA, 2018, 44(2): 280-288. doi: 10.16383/j.aas.2018.c160704
Citation: ZHANG Cheng-Kun, HAN Min. Spectral-spatial Joint Classification of Hyperspectral Image with Edge-preserving Filtering. ACTA AUTOMATICA SINICA, 2018, 44(2): 280-288. doi: 10.16383/j.aas.2018.c160704

基于边缘保持滤波的高光谱影像光谱-空间联合分类

doi: 10.16383/j.aas.2018.c160704
基金项目: 

中央高校基本科研业务费(重点类项目) DUT17ZD216

国家自然科学基金 61374154

国家自然科学基金委科学仪器基础研究专项 51327004

国家自然科学基金 61773087

详细信息
    作者简介:

    张成坤   大连理工大学电子信息与电气工程学部博士研究生.主要研究方向为遥感图像处理, 高光谱影像分类.E-mail:zhangchengkundon@mail.dlut.edu.cn

    通讯作者:

    韩敏   大连理工大学电子信息与电气工程学部教授.主要研究方向为模式识别, 复杂系统建模与分析及时间序列预测.本文通信作者.E-mail:minhan@dlut.edu.cn

Spectral-spatial Joint Classification of Hyperspectral Image with Edge-preserving Filtering

Funds: 

Fundamental Research Funds for the Central Universities DUT17ZD216

National Natural Science Foundation of China 61374154

Special Fund for Basic Research on Scientific Instruments of the National Natural Science Foundation of China 51327004

National Natural Science Foundation of China 61773087

More Information
    Author Bio:

     Ph. D. candidate at the Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology. His research interest covers remote sensing image processing and hyperspectral data classification

    Corresponding author: HAN Min   Professor at the Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology. Her research interest covers pattern recognition, modeling and analysis of complex system, and time series prediction. Corresponding author of this paper
  • 摘要: 针对高光谱遥感影像分类过程中,高维数据引起的"维数灾难"以及空间邻域一致性信息没有得到充分利用的问题,提出一种基于边缘保持滤波(Edge-preserving filtering,EPF)的高光谱影像光谱-空间联合分类算法.该算法首先进行波段子集划分和主成分提取,构造新的低维特征集,在保存影像结构信息的前提下降低数据维度;其次利用支持向量机(Support vector machine,SVM)获得低维特征集的初始分类概率图;然后利用原始影像主成分对初始分类概率图进行边缘保持滤波,融合光谱信息和空间信息;最后根据滤波后分类概率图对应像素点值的大小确定每个像素的类别.在Indian Pines和Pavia University两组高光谱数据上进行仿真实验,相同实验条件下,本文算法都获得最高分类精度和最少的时间消耗.仿真结果表明本文算法在高光谱遥感影像分类任务中具有明显的优势.
    1)  本文责任编委 桑农
  • 图  1  算法主要流程

    Fig.  1  The procedure of the proposed method

    图  2  初始分类概率图双边滤波效果

    Fig.  2  Bilateral filtering result of initial probabilistic map

    图  3  Indian Pines数据集波段子集$K$对分类精度的影响

    Fig.  3  OA of the proposed methods with different numbers of band subsets $K$ in Indian Pines dataset

    图  4  Indian Pines影像双边滤波器参数对分类精度的影响

    Fig.  4  The influence of the parameters of Bilateral filter in Indian Pines image

    图  5  Indian Pines影像引导滤波器参数对分类精度的影响

    Fig.  5  The influence of the parameters of Guided filter in Indian Pines image

    图  6  Indian Pines数据集不同方法分类效果图

    Fig.  6  Classification maps for the Indian Pines dataset using different methods

    图  7  数据集波段子集$K$对分类精度的影响

    Fig.  7  OA of the proposed methods with different numbers of band subsets $K$ in Pavia University dataset

    图  8  Pavia University数据集不同方法分类效果图

    Fig.  8  Classification maps for the Pavia University dataset using different methods

    表  1  Indian Pines数据集不同方法分类精度

    Table  1  Classification accuracy for the Indian Pines dataset using different methods

    类别训练样本测试样本SVM (%) SVMCK (%) EPF-B-g (%) BFSVM-PC1 (%) BFSVM-PC3 (%) GFSVM-PC1 (%) GFSVM-PC3 (%)
    183873.6875.0090.91 ${\textbf{100.00}} $${\textbf{100.00}}$${\textbf{100.00}}$${\textbf{100.00}}$
    21431 28577.3789.3193.17${\textbf{99.83}}$99.5899.59${\textbf{99.83}}$
    38374778.1388.81${\textbf{98.98}}$97.4697.5997.5897.72
    42421376.2777.2596.30${\textbf{98.98}}$${\textbf{98.98}}$ 98.5198.53
    54843592.3094.8599.0298.8298.82${\textbf{99.52}}$ 98.81
    67365790.4398.8197.7699.8599.85${\textbf{100.00}}$99.85
    782088.8893.75 ${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$
    84843097.4898.18${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$ $ {\textbf{100.00}}$ ${\textbf{100.00}}$
    981238.09 ${\textbf{100.00}} $ ${\textbf{100.00}}$ ${\textbf{100.00}}$ $ {\textbf{100.00}}$ $\textbf{100.00} $ ${\textbf{100.00}}$
    109787577.0585.3093.6198.7498.8999.1398.76
    112462 20980.4692.98 ${\textbf{95.38}}$ 94.4794.1394.0193.73
    125953479.3487.1691.5896.3296.15${\textbf{97.94}}$ $ {\textbf{97.94}}$
    132118487.8097.9199.46$ {\textbf{100.00}}$ ${\textbf{100.00}}$$ {\textbf{100.00}}$ ${\textbf{100.00}}$
    141271 13890.9396.82 ${\textbf{97.76}}$ 97.1497.1595.9097.57
    153934774.8973.1094.7496.6596.3596.20${\textbf{97.01}}$
    1698490.6996.4792.41${\textbf{98.67}}$98.5198.4898.59
    OA (%) 82.8791.2895.8497.4297.3397.29${\textbf{97.43}}$
    AA (%) 80.8690.3696.3298.5698.5098.55${\textbf{98.65}}$
    $\kappa$ 系数0.80380.90040.9530.9710.9690.969${\textbf{0.971}}$
    时间(s)159.42210.44159.4734.0033.25 ${\textbf{29.42}}$ 32.91
    下载: 导出CSV

    表  2  Pavia University数据集不同方法分类精度

    Table  2  Classification accuracy for the Pavia University dataset using different methods

    类别训练样本测试样本SVM (%) SVMCK (%) EPF-B-g (%) BFSVM-PC1 (%) BFSVM-PC3 (%) GFSVM-PC1 (%) GFSVM-PC3 (%)
    12656 36692.9196.97${\textbf{98.11}} $95.1295.1295.1294.87
    274617 90396.07$ {\textbf{99.54}} $97.2599.2099.2299.2499.49
    3842 01580.9785.5199.94 ${\textbf{100.00}}$ ${\textbf{100.00}}$99.83${\textbf{100.00}}$
    41232 94195.1895.3199.7399.6799.6499.86${\textbf{100.00}}$
    5541 29198.0999.85${\textbf{100.00}}$ ${\textbf{100.00}}$$ {\textbf{100.00}}$99.9299.92
    62014 82888.7296.21${\textbf{98.87}}$98.6498.6498.7398.75
    7531 27785.8494.13${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$ ${\textbf{100.00}}$
    81473 53586.2292.5391.6592.9993.0192.77${\textbf{93.61}}$
    938909 ${\textbf{100.00}}$ ${\textbf{100.00}}$${\textbf{100.00}}$${\textbf{100.00}}$ ${\textbf{100.00}}$ $\textbf{100.00}$ ${\textbf{100.00}}$
    OA (%) 92.9297.0097.5598.0598.0698.07${\textbf{98.23}}$
    AA (%) 91.5696.5698.3998.4098.4098.39${\textbf{98.52}}$
    $\kappa$ 系数0.90610.96020.9670.9740.9740.974${\textbf{0.977}}$
    时间(s)94.56178.3297.4847.2247.01 ${\textbf{28.98}}$47.37
    下载: 导出CSV
  • [1] 潘宗序, 禹晶, 肖创柏, 孙卫东.基于光谱相似性的高光谱图像超分辨率算法.自动化学报, 2014, 40(12):2797-2807 http://www.aas.net.cn/CN/abstract/abstract18558.shtml

    Pan Zong-Xu, Yu Jing, Xiao Chuang-Bai, Sun Wei-Dong. Spectral similarity-based super resolution for hyperspectral images. Acta Automatica Sinica, 2014, 40 (12):2797-2807 http://www.aas.net.cn/CN/abstract/abstract18558.shtml
    [2] Du B, Zhang L P. Target detection based on a dynamic subspace. Pattern Recognition, 2014, 47 (1):344-358 doi: 10.1016/j.patcog.2013.07.005
    [3] Plaza A, Benediktsson J A, Boardman J W, Brazile J, Bruzzone L, Camps-Valls G, Chanussot J, Fauvel M, Gamba P, Gualtieri A, Marconcini M, Tilton J C, Trianni G. Recent advances in techniques for hyperspectral image processing. Remote Sensing of Environment, 2009, 113 (S1):S110-S122
    [4] Jia X P, Kuo B C, Crawford M M. Feature mining for hyperspectral image classification. Proceedings of the IEEE, 2013, 101 (3):676-697 doi: 10.1109/JPROC.2012.2229082
    [5] Han M, Liu B. Ensemble of extreme learning machine for remote sensing image classification. Neurocomputing, 2015, 149:65-70 doi: 10.1016/j.neucom.2013.09.070
    [6] Ramzi P, Samadzadegan F, Reinartz P. Classification of hyperspectral data using an AdaBoostSVM technique applied on band clusters. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7 (6):2066-2079 doi: 10.1109/JSTARS.2013.2292901
    [7] 倪鼎, 马洪兵.基于近邻协同的高光谱图像谱-空联合分类.自动化学报, 2015, 41 (2):273-284 http://www.aas.net.cn/CN/abstract/abstract18606.shtml

    Ni Ding, Ma Hong-Bing. Spectral-spatial classification of hyperspectral images based on neighborhood collaboration. Acta Automatica Sinica, 2015, 41 (2):273-284 http://www.aas.net.cn/CN/abstract/abstract18606.shtml
    [8] Zhang Z, Pasolli E, Crawford M M, Tilton J C. An active learning framework for hyperspectral image classification using hierarchical segmentation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9 (2):640-654 doi: 10.1109/JSTARS.2015.2493887
    [9] Fauvel M, Tarabalka Y, Benediktsson J A, Chanussot J, Tilton J C. Advances in spectral-spatial classification of hyperspectral images. Proceedings of the IEEE, 2013, 101 (3):652-675 doi: 10.1109/JPROC.2012.2197589
    [10] Ji R R, Gao Y, Hong R C, Liu Q, Tao D C, Li X L. Spectral-spatial constraint hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52 (3):1811-1824 doi: 10.1109/TGRS.2013.2255297
    [11] Camps-Valls G, Gomez-Chova L, Munoz-Marí J, Vila-Francés J, Calpe-Maravilla J. Composite kernels for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 2006, 3 (1):93-97 doi: 10.1109/LGRS.2005.857031
    [12] Benediktsson J A, Palmason J A, Sveinsson J R. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43 (3):480-491 doi: 10.1109/TGRS.2004.842478
    [13] Tarabalka Y, Chanussot J, Benediktsson J A. Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognition, 2010, 43 (7):2367-2379 doi: 10.1016/j.patcog.2010.01.016
    [14] Li X R, Pan J, He Y Q, Liu C S. Bilateral filtering inspired locality preserving projections for hyperspectral images. Neurocomputing, 2015, 164:300-306 doi: 10.1016/j.neucom.2015.01.021
    [15] Kang X D, Li S T, Benediktsson J A. Spectral-spatial hyperspectral image classification with edge-preserving filtering. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52 (5):2666-2677 doi: 10.1109/TGRS.2013.2264508
  • 加载中
图(8) / 表(2)
计量
  • 文章访问数:  2171
  • HTML全文浏览量:  342
  • PDF下载量:  710
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-10-09
  • 录用日期:  2017-02-21
  • 刊出日期:  2018-02-20

目录

    /

    返回文章
    返回