Please wait a minute...
国土资源遥感  2019, Vol. 31 Issue (2): 24-31    DOI: 10.6046/gtzyyg.2019.02.04
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
基于优势集聚类和马尔科夫随机场的高光谱图像分类算法
曲海成,郭月(),王媛媛
辽宁工程技术大学软件学院,葫芦岛 125105
Hyperspectral image classification based on dominant sets clustering and Markov random fields
Haicheng QU,Yue GUO(),Yuanyuan WANG
College of Software, Liaoning Technical University, Huludao 125105, China
全文: PDF(4806 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

为充分利用高光谱图像自身丰富的光谱信息和空间信息,提出一种基于优势集聚类和马尔科夫随机场相结合的高光谱图像分类算法。首先,分析高光谱图像局部空谱一致性,完成对波段信息量和差异程度的度量,构造无向加权图,利用优势集聚类方法选择出保留良好结构信息的最优波段子集; 其次,通过马尔科夫随机场对波段选择后的相邻像元建立局部空谱一致性,有效利用图像空间上下文信息; 最后,根据贝叶斯定理,将高光谱图像分类问题转化为最大后验概率的求解问题,从而获得分类结果。2个经典数据集(Indian Pines和Pavia University)的实验表明,相比其他同类算法,该算法能达到更高的总体分类精度和Kappa系数。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
曲海成
郭月
王媛媛
关键词 优势集聚类波段选择马尔科夫随机场高光谱图像分类    
Abstract

In order to make full use of the abundant spectral information and spatial information of hyperspectral images, this paper proposes a hyperspectral image classification algorithm based on dominant sets clustering and Markov random fields. First of all, the local spectral-spatial consistency of hyperspectral images is analyzed, the measurement of both band informativeness and independence is completed, an un-directed weighting graph is constructed and dominant sets clustering method is used to select the optimal band subset which preserves good structure information. Secondly, the local spectral-spatial consistency of adjacent pixels after the band selection is established by using Markov random fields, which makes the context information of the image space effectively used. Finally, according to the Bayesian theorem, the hyperspectral image classification problem is transformed into the maximum posterior probability which can solve the problem and yield the classification results. Experiments on two datasets, i.e., Indian Pines and Pavia University, show that this algorithm can achieve higher overall classification accuracy and Kappa coefficient than other similar algorithms.

Key wordsdominant sets    clustering    band selection    Markov random fields    hyperspectral image    classification
收稿日期: 2018-03-12      出版日期: 2019-05-23
ZTFLH:  TP751  
基金资助:国家自然科学基金青年基金项目“面向宽幅高光谱遥感影像的高效压缩方法研究”(41701479);生产技术问题创新研究基金项目“卫星遥感图像大数据压缩与快速处理技术”共同资助(20160092T)
通讯作者: 郭月     E-mail: GY_Gina@163.com
作者简介: 曲海成(1981-),男,副教授,博士,主要从事高光谱遥感影像高性能计算方面研究。Email: haichengqu@hit.edu.cn。
引用本文:   
曲海成,郭月,王媛媛. 基于优势集聚类和马尔科夫随机场的高光谱图像分类算法[J]. 国土资源遥感, 2019, 31(2): 24-31.
Haicheng QU,Yue GUO,Yuanyuan WANG. Hyperspectral image classification based on dominant sets clustering and Markov random fields. Remote Sensing for Land & Resources, 2019, 31(2): 24-31.
链接本文:  
http://www.gtzyyg.com/CN/10.6046/gtzyyg.2019.02.04      或      http://www.gtzyyg.com/CN/Y2019/V31/I2/24
Fig.1  DSSM算法流程
Tab.1  Indian Pines数据集的真实地物类别标记信息
Tab.2  Pavia University数据集的真实地物类别标记信息
Fig.2  DSSM算法在不同特征数下的总体分类精度
Fig.3  Indian Pines数据集上不同算法的分类结果
Fig.4  Pavia University数据集上不同算法的分类结果
数据集 评价指标 SVM算法 DS-SVM算法 DS-KNN算法 DS-RT算法 DSSM算法
Indian Pines OA/% 78.35 83.36 73.31 71.69 93.19
Kappa 0.751 3 0.809 4 0.694 9 0.746 8 0.921 9
Pavia University OA/% 94.27 92.08 84.84 85.70 97.80
Kappa 0.923 9 0.894 4 0.745 7 0.748 9 0.973 0
Tab.3  不同算法的总体分类精度
[1] 叶珍, 白璘, 粘永健 . 基于Gabor特征与局部保护降维的高光谱图像分类算法[J]. 光学学报, 2016,36(10):504-513.
Ye Z, Bai L, Nian Y J . Hyperspectral image classification algorithm based on Gabor feature and locality-preserving dimensionality reduction[J]. Acta Optica Sinica, 2016,36(10):504-513.
[2] 侯榜焕, 张耿, 王飞 , 等. 结合多尺度空间滤波和层级网络的基于结构保持的高光谱波段选择[J]. 光子学报, 2017,46(5):179-188.
Hou B H, Zhang G, Wang F , et al. Feature selection based on structure preserving for hyperspectral image combination with multi-scale spatial filtering and hierarchical network[J]. Acta Photonica Sinica, 2017,46(5):179-188.
[3] Li J, Zhang H, Zhang L . Efficient superpixel-level multitask joint sparse representation for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015,53(10):5338-5351.
doi: 10.1109/TGRS.2015.2421638
[4] Albarracin J F H, Santos J A D, Torres R D S. Learning to combine spectral indices with genetic programming [C]//29th SIBGRAPI Conference on Graphics,Patterns and Images.Sao Paulo:IEEE, 2017: 408-415.
[5] Vaiphasa C, Skidmore A K , Boer W F D ,et al.A hyperspectral band selector for plant species discrimination[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007,62(3):225-235.
doi: 10.1016/j.isprsjprs.2007.05.006
[6] Martínez-Usómartinez-Uso A, Pla F, Sotoca J M , et al. Clustering-based hyperspectral band selection using information measures[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007,45(12):4158-4171.
doi: 10.1109/TGRS.2007.904951
[7] Hou J, Xu E, Chi L, et al. Robust clustering based on dominant sets [C]//22nd International Conference on Pattern Recognition.Stockholm:IEEE, 2014: 1466-1471.
[8] Hou J, Pelillo M . A simple feature combination method based on dominant sets[J]. Pattern Recognition, 2013,46(11):3129-3139.
doi: 10.1016/j.patcog.2013.04.005
[9] Zhu G K, Huang Y C, Lei J S , et al. Unsupervised hyperspectral band selection by dominant set extraction[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016,54(1):227-239.
doi: 10.1109/TGRS.2015.2453362
[10] Pavan M, Pelillo M . Dominant sets and pairwise clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(1):167-172.
doi: 10.1109/TPAMI.2007.250608
[11] Hou J, Xu E, Liu W X , et al. A density-based enhancement to dominant sets clustering[J]. IET Computer Vision, 2013,7(5):354-361.
doi: 10.1049/iet-cvi.2013.0072
[12] Yang X, Liu H, Latecki L J . Contour-based object detection as dominant set computation[J]. Pattern Recognition, 2012,45(5):1927-1936.
doi: 10.1016/j.patcog.2011.11.010
[13] Hamid R, Maddi S, Johnson A , et al. A novel sequence representation for unsupervised analysis of human activities[J]. Artificial Intelligence, 2009,173(14):1221-1244.
doi: 10.1016/j.artint.2009.05.002
[14] 贺金鑫, 陈圣波, 王阳 , 等. 一种基于朴素贝叶斯分类模型的高光谱矿物精确识别方法[J]. 光谱学与光谱分析, 2014,34(2):505-509.
He J X, Chen S B, Wang Y , et al. An accurate approach to hyperspectral mineral identification based on naive Bayesian classification model[J]. Spectroscopy and Spectral Analysis, 2014,34(2):505-509.
[15] Zhao J, Zhong Y, Shu H , et al. High-resolution image classification integrating spectral-spatial-location cues by conditional random fields[J]. IEEE Transactions on Image Processing, 2016,25(9):4033-4045.
doi: 10.1109/TIP.2016.2577886
[16] Tarabalka Y, Rana A. Graph-cut-based model for spectral-spatial classification of hyperspectral images [C]//2014 IEEE International Geoscience and Remote Sensing Symposium(IGARSS).Quebec:IEEE, 2014: 3418-3421.
[17] Moser G, Serpico S B, Benediktsson J A . Land-cover mapping by Markov modeling of spatial-contextual information in very-high-resolution remote sensing images[J]. Proceedings of the IEEE, 2013,101(3):631-651.
doi: 10.1109/JPROC.2012.2211551
[18] 鲍蕊, 薛朝辉, 张像源 , 等. 综合聚类和上下文特征的高光谱影像分类[J]. 武汉大学学报(信息科学版), 2017,42(7):890-896.
Bao R, Xue Z H, Zhang X Y , et al. Classification merged with clustering and context for hyperspectral imagery[J]. Geomatics and Information Science of Wuhan University, 2017,42(7):890-896.
[19] Boykov Y, Veksler O, Zabih R . Fast approximate energy minimization via graph cuts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(11):1222-1239.
doi: 10.1109/34.969114
[1] 傅锋,王新杰,汪锦,王娜,佟济宏. 高分二号影像树种识别及龄组划分[J]. 国土资源遥感, 2019, 31(2): 118-124.
[2] 陈震,张耘实,章远钰,桑玲玲. 高标准农田建后遥感监测方法[J]. 国土资源遥感, 2019, 31(2): 125-130.
[3] 韩衍欣,蒙继华. 面向地块的农作物遥感分类研究进展[J]. 国土资源遥感, 2019, 31(2): 1-9.
[4] 阿茹罕,何芳,王标标. 加权空-谱主成分分析的高光谱图像分类[J]. 国土资源遥感, 2019, 31(2): 17-23.
[5] 李莹,于海洋,王燕,吴建鹏,杨礼. 基于无人机重建点云与影像的城市植被分类[J]. 国土资源遥感, 2019, 31(1): 149-155.
[6] 冯娟,丁建丽,魏雯瑜. 基于雷达数据的区域土壤盐渍化监测[J]. 国土资源遥感, 2019, 31(1): 195-203.
[7] 涂兵,张晓飞,张国云,王锦萍,周瑶. 递归滤波与KNN的高光谱遥感图像分类方法[J]. 国土资源遥感, 2019, 31(1): 22-32.
[8] 郭拯危,王乐,宋国磊. 基于混合模糊的SAR图像水陆分割算法[J]. 国土资源遥感, 2018, 30(4): 62-67.
[9] 薛娟,俞琳锋,林起楠,刘广,黄华国. 基于Sentinel-1多时相InSAR影像的云南松切梢小蠹危害程度监测[J]. 国土资源遥感, 2018, 30(4): 108-114.
[10] 刘昭华,张春艳. 开封市城市扩张动态监测及驱动因子分析[J]. 国土资源遥感, 2018, 30(4): 193-199.
[11] 国贤玉,李坤,王志勇,李宏宇,杨知. 基于SVM+SFS策略的多时相紧致极化SAR水稻精细分类[J]. 国土资源遥感, 2018, 30(4): 20-27.
[12] 张康,黑保琴,李盛阳,邵雨阳. 基于CNN模型的遥感图像复杂场景分类[J]. 国土资源遥感, 2018, 30(4): 49-55.
[13] 刘万军,李天慧,曲海成. 基于Fisher准则和TrAdaboost的高光谱相似样本分类算法[J]. 国土资源遥感, 2018, 30(4): 41-48.
[14] 杨军,裴剑杰. 一种改进的ICM遥感影像分割算法[J]. 国土资源遥感, 2018, 30(3): 18-25.
[15] 吕野,胡翔云. 利用增量式马尔科夫随机场分割提取高空间分辨率遥感影像道路[J]. 国土资源遥感, 2018, 30(3): 76-82.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《国土资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 Email:gtzyyg@agrs.cn; gtzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发