Semi-supervised Graph-based Hyperspectral Image Classification with Active Learning

doi:10.11947/j.AGCS.2015.20140221

Abstract

Abstract:

Currently, it is difficult and time-consuming to obtain enough labeled samples for hyperspectral image(HSI) classification, while numerous unlabeled samples can be easily identified but unused. Here, in order to overcome these shortcomings, we proposed a semi-supervised graph-based combined with active learning mechanism approach in this paper. Firstly, we extracted the spatio-spectral feature by reorganizing the spectrum of a pixel with its neighbors, followed by a sorting scheme to make the feature representation to be rotation invariant. Then, the most uncertain samples(namely largest ambiguity samples for classifier) were selected for operator to label with active learning algorithm. Finally, both labeled samples and unlabeled samples were used for semi-supervised classification. The proposed algorithm could guarantee that boundary samples were selected, which would help construct the boundary of a classifier. Simultaneously, even when less labeled samples were available, the proposed method achieved a good classification result by introducing a large number of unlabeled samples. The experimental results on three real hyperspectral images confirmed that the proposed method can obtain higher classification accuracy.

Key words: hyperspectral image classification, semi-supervised graph-based learning, active learning, spatio-spectral feature

CLC Number:

P237

TIAN Yanping, TAO Chao, ZOU Zhengrong, YANG Zhaoxia, HE Xiaofei. Semi-supervised Graph-based Hyperspectral Image Classification with Active Learning[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(8): 919-926.

References

[1] PENN B S. Using Simulated Annealing to Obtain Optimal Linear End-member Mixtures of Hyperspectral Data[J]. Computers & Geosciences, 2002, 28(7): 809-817.
[2] RICHARDS J A. Remote Sensing Digital Image Analysis[M]. Berlin: Springer, 1999.
[3] LI Hui, WANG Yunpeng, LI Yan, et al. Unmixing of Remote Sensing Images Based on Support Vector Machines and Pairwise Coupling[J]. Acta Geodaetica et Cartographica Sinica, 2009, 38(4): 318-323. (李慧, 王云鹏, 李岩, 等. 基于SVM和PWC的遥感影像混合像元分解[J]. 测绘学报, 2009, 38(4): 318-323.)
[4] JIN Jing, ZOU Zhengrong, TAO Chao. Compressed Texton Based High Resolution Remote Sensing Image Classification[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5): 493-499. (金晶, 邹峥嵘, 陶超. 高分辨率遥感影像的压缩纹理元分类[J]. 测绘学报, 2014, 43(5): 493-499.)
[5] GUO Xiujuan, YUAN Yue, FAN Xiaoou. Analysis and Application of Fuzzy Clustering Algorithm[J]. Journal of Jilin Institute of Architecture & Civil Engineering, 2009, 26(4): 79-81. (郭秀娟, 袁月, 范小鸥. 模糊聚类算法分析及应用[J]. 吉林建筑工程学院学报, 2009, 26(4): 79-81.)
[6] BOVOLO F, BRUZZONE L, CARLIN L. A Novel Technique for Subpixel Image Classification Based on Support Vector Machine[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2983-2999.
[7] ZHU X J. Semi-supervised Learning Literature Survey[OL/EB]. Wisconsin: University of Wisconsin, 2008.[2013-11-23]. http://pages.cs.wisc.edu/~jerryzhu/research/ssl/semireview.html.
[8] TUIA D, CAMPS-VALLS G. Semisupervised Remote Sensing Image Classification with Cluster Kernels[J]. IEEE Transactions on Geoscience and Remote Sensing Letters, 2009, 6(2): 224-228.
[9] LIU Xiaofang, HE Binbin, LI Xiaowen. Classification for Beijing-1 Micro-satellite's Multispectral Image Based on Semi-supervised Kernel FCM Algotithm[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(3): 301-306. (刘小芳, 何彬彬, 李小文. 基于半监督核模糊c-均值算法的北京一号小卫星多光谱图像分类[J]. 测绘学报, 2011, 40(3): 301-306.)
[10] DOPIDO I, LI J, PLAZA A, et al. Semi-supervised Classification of Hyperspectral Data Using Spectral Unmixing Concepts[C]//Proceedings of the 2012 Tyrrhenian Workshop on Advances in Radar and Remote Sensing. Naples: IEEE, 2012: 353-358.
[11] BRUZZONE L, CHI M, MARCONCINI M. A Novel Transductive SVM for Semisupervised Classification of Remote-sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(11): 3363-3373.
[12] DÓPIDO I, LI J, MARPU P R, et al. Semisupervised Self-learning for Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(7): 4032-4044.
[13] CAMPS-VALLS G, BANDOS MARSHEVA T, ZHOU D. Semi-supervised Graph-based Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(10): 3044-3054.
[14] GU Y F, FENG K. L1-graph Semisupervised Learning for Hyperspectral Image Classification[C]//Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium. Munich: IEEE, 2012: 1401-1404.
[15] JOSHI A J, PORIKLI F, PAPANIKOLOPOULOS N. Multi-class Active Learning for Image Classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009: 2372-2379.
[16] HOTELLING H. Analysis of A Complex of Statistical Variables into Principal Components[J]. Journal of Educational Psychology, 1933, 24(6): 417-441.
[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] CRAWFORD M M, TUIA D, YANG H L. Active Learning: Any Value for Classification of Remotely Sensed Data?[J]. Proceedings of the IEEE, 2013, 101(3): 593-608.
[19] LONG Jun, YIN Jianping, ZHU En, et al. An Active Learning Algorithm by Selecting the Most Possibly Wrong-Predicted Instances[J]. Journal of Computer Research and Development, 2008, 45(3): 472-478. (龙军, 殷建平, 祝恩, 等. 选取最大可能预测错误样例的主动学习算法[J]. 计算机研究与发展, 2008, 45(3): 472-478.)
[20] LAN Yuandong. Research on Theory, Algorithms and Application of Graph-based Semi-supervised Learning[D]. Guangzhou: South China University of Technology, 2012. (兰远东. 基于图的半监督学习理论、算法及应用研究[D]. 广州: 华南理工大学, 2012.)