A Semi-supervised Classification Method for Hyperspectral Images

doi:10.13474/j.cnki.11-2246.2018.0042

Abstract

Abstract:

Based on density sampling and dynamic time warping distance, this paper proposes a semi-supervised fuzzy cluster method to partition hyperspectral data set into several groups. The labeled samples are first obtained by density sampling method. Then the dynamic time warping distance is computed between a pair of samples. Lastly, semi-supervised fuzzy c-means is employed to cluster the hyperspectral image. To validate the proposed method, the Indian Pines and Pavia U data sets are chosen to feed our method. The experimental results show that it can discover the ideal clusters by the proposed method.

Key words: hyperspectral image, dynamic time warping distance, semi-supervised fuzzy clustering, density sampling

CLC Number:

P237

LI Caihong, ZHAO Yifei. A Semi-supervised Classification Method for Hyperspectral Images[J]. 测绘通报, 2018, 0(2): 46-49.

References

[1] 杨国鹏,余旭初,冯伍法,等.高光谱遥感技术的发展与应用现状[J].测绘通报,2008(10):1-4.
[2] 杜培军,夏俊士,薛朝辉.高光谱遥感影像分类研究进展[J].遥感学报,2016, 20(2):236-256.
[3] 张良培, 黄昕. 遥感影像信息处理技术的研究进展[J].遥感学报,2009, 13(4):559-569.
[4] 于文博,王忠勇,李山山,等. 整合超像元分割和峰值密度的高光谱图像聚类[J].中国图象图形学报,2016,21(10):1402-1410.
[5] 杨凯歌,冯学智,肖鹏峰,等. 优化子空间SVM集成的高光谱图像分类[J].遥感学报,2016, 20(3):409-419.
[6] 李宠,谷琼,蔡之华,等. 改进的主动学习算法及在高光谱分类中的应用[J]. 华中科技大学学报(自然科学版),2013, 41(S2):274-278.
[7] 孙乐,吴泽彬,冯灿, 等. 一种新的两分类器融合的空谱联合高光谱分类方法[J].电子学报,2015,43(11):2210-2217.
[8] 王俊淑,江南,张国明, 等. 融合光谱一空间信息的高光谱遥感影像增量分类算法[J].测绘学报,2015,44(9):1003-1013.
[9] 程志会,谢福鼎. 基于空间特征和纹理信息的高光谱图像半监督分类[J].测绘通报,2016(12):56-59.
[10] 罗甫林.高光谱图像稀疏流形学习方法研究[J].测绘学报,2017,46(3):400.
[11] 谢福鼎,李壮, 基于改进的半监督FCM算法的高光谱遥感影像分类[J]. 测绘通报, 2016(9):60-62.
[12] 邵远杰,吴国平,马丽.属类概率距离构图的半监督高光谱图像分类[J].测绘学报,2014,43(11):1182-1189.
[13] HUANG J B, SUN H L, KANG J M, et al. ESC:An Efficient Synchronization-based Clustering Algorithm[J]. Knowledge-based Systems, 2013, 40:111-122.
[14] KOLLIOS G, GUNOPULOS D, KOUDAS N, et al. Efficient Biased Sampling for Approximate Clustering and Outlier Detection in Large Data Sets[J]. IEEE Transactions on Knowledge and Data Engineering, 2003, 15(5):1170-1187.
[15] MACIEJ L. Hierarchical Clustering of Time Series Data with Parametric Derivative Dynamic Time Warping[J]. Expert Systems with Applications,2016, 62(15):116-130.
[16] PEDRYC Z W, WALETZKY J. Fuzzy Clustering with Partial Supervision[J]. IEEE Transactions on Systems Man & Cybernetics Part B, 1997, 27(5):787-795.
[17] TUIA D, VOLPI M, COPA L, et al. A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(3):606-617.
[18] TONG L, KRAMER K, SAMSON S, et al. Active Learning to Recognize Multiple Types of Plankton[J]. Journal of Machine Learning Research, 2004,6(4):478-481.
[19] TUIA D, RATLE F, PACIFICI F, et al. Active Learning Methods for Remote Sensing Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(7):2218-2232.
[20] LI J, BIOUCAS J M, PLAZA A. Hyperspectral Image Segmentation Using a New Bayesian Approach with Active Learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(10):3947-3960.