Nonlinear Spectral Unmixing for Optimizing Per-pixel Endmember Sets

doi:10.11947/j.AGCS.2016.20140520

Abstract

Abstract: For a given pixel, fractional abundances predicted by spectral mixture analysis (SMA) are most accurate when only the endmembers that comprise it are used. This paper presents a support vector machines (SVM) method to achieve land use/land cover fractions of remote sensing image using two steps: ①defining the optimal per-pixel endmember set, which removes endmembers based on negative fractional abundances generated by SVM method; ②using SVM extended with pairwise coupling (PWC) to output probabilities as the abundance of landscape fractions. The performances of the proposed method were evaluated with the multiple endmember spectral mixture analysis (MESMA) method, which has been widely applied to map land cover for the goodness of the model fitting. The results obtained in this study were validated by real fractions generated from SPOT high resolution geometric (HRG) image. The best classification results were obtained by the proposed method indicated by the lower total mean absolute error, the higher overall accuracy, and the higher kappa. From this study, the proposed method is proved to be effective in obtaining abundance fractions that are physically realistic (sum close to one and nonnegative), and providing valuable application in selecting endmembers that occur within a pixel.

Key words: remote sensing image, pixel unmixing, selective endmember, support vector machines (SVM), nonlinear unmixing

CLC Number:

P237

LI Hui, ZHANG Jinqu, CAO Yang, WANG Xingfang. Nonlinear Spectral Unmixing for Optimizing Per-pixel Endmember Sets[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(1): 80-86.

References

[1] 刘正春, 曾永年, 何丽丽, 等. 基于光谱归一化的变组分光谱混合分析(NMESMA)方法及其应用[J]. 遥感技术与应用, 2012, 27(2): 159-167. LIU Zhengchun, ZENG Yongnian, HE Lili, et al. Method of Normalized Multiple Endmember Spectral Mixture Analysis and Its Application[J]. Remote Sensing Technology and Application, 2012, 27(2): 159-167.
[2] 陈述彭, 童庆禧, 郭华东. 遥感信息机理研究[M]. 北京: 科学出版社, 1998. CHEN Shupeng, TONG Qinxi, GUO Huadong. Research on Mechanism of Remote Sensing Information[M]. Beijing: Science Press, 1998.
[3] 王旭红, 郭建明, 贾百俊, 等. 元胞自动机的遥感影像混合像元分类[J]. 测绘学报, 2008, 37(1): 42-48. WANG Xuhong, GUO Jianming,JIA Baijun, et al. Mixed Pixels Classification of Remote Sensing Images Based on Cellular Automata[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(1): 42-48.
[4] SOMERS B, ASNER G P, TITS L, et al. Endmember Variability in Spectral Mixture Analysis: A Review[J]. Remote Sensing of Environment, 2011, 115(7): 1603-1616.
[5] 吴波, 熊助国. 基于光谱最佳尺度分割特征的高光谱混合像元分解[J]. 测绘学报, 2012, 41(2): 205-212. WU Bo,XIONG Zhuguo.Unmixing of Hyperspectral Mixture Pixels Based on Spectral Multiscale Segemented Features[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(2): 205-212.
[6] ZARE A, HO K C. Endmember Variability in Hyperspectral Analysis: Addressing Spectral Variability during Spectral Unmixing[J]. IEEE Signal Processing Magazine, 2014, 31(1): 95-104.
[7] BEDINI E.Mapping Lithology of the Sarfartoq Carbonatite Complex,Southern West Greenland, Using HyMap Imaging Spectrometer Data[J]. Remote Sensing of Environment, 2009, 113(6): 1208-1219.
[8] 丁建丽, 姚远. 干旱区绿洲典型地物MESMA模拟分解与验证[J]. 地球信息科学学报, 2013, 15(3): 452-460. DING Jianli, YAO Yuan. Research on Pixel Unmixing of Typical Surface Features in Oasis Based on the MESMA Model[J]. Journal of Geo-Information Science, 2013, 15(3): 452-460.
[9] BACHMANN C M, AINSWORTH T L, FUSINA R A. Improved Manifold Coordinate Representations of Large-Scale Hyperspectral Scenes[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(10): 2786-2803.
[10] 吴波, 袁春. 非线性混合像元分解的可视化分析与评价[J]. 中国图象图形学报, 2010, 15(1): 167-173. WU Bo, YUAN Chun. Visualized Analysis and Evaluation of Nonlinear Unmixing the Mixed Pixels[J]. Journal of Image and Graphics, 2010, 15(1): 167-173.
[11] BROADWATER J, BANERJEE A. A Generalized Kernel for Areal and Intimate Mixtures[C]//Proceedings of the 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. Reykjavik: IEEE, 2010: 1-4.
[12] BROADWATER J, BANERJEE A. Mapping Intimate Mixtures Using An Adaptive Kernel-based Technique[C]//Proceedings of the 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. Lisbon: IEEE, 2011: 1-4.
[13] PLAZA J, PLAZA A. Spectral Mixture Analysis of Hyperspectral Scenes using Intelligently Selected Training Samples[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(2): 371-375.
[14] ALTMANN Y, DOBIGEON N, TOURNERET J Y, et al. Nonlinear Unmixing of Hyperspectral Images using Radial Basis Functions and Orthogonal Least Squares[C]//Proceedings of IEEE International Conference Geoscience and Remote Sensing Symposium. Vancouver: IEEE, 2011: 1151-1154.
[15] LICCIARDI G A, DEL F F. Pixel Unmixing in Hyperspectral Data by Means of Neural Networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(11): 4163-4172.
[16] ALTMANN Y, HALIMI A, DOBIGEON N, et al. Supervised Nonlinear Spectral Unmixing Using a Postnonlinear Mixing Model for Hyperspectral Imagery[J]. IEEE Transactions on Image Processing, 2012, 21(6): 3017-3025.
[17] VLADIMIR N V. The Nature of Statistical Learning Theory[M]. New York: Springer, 1998.
[18] 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.
[19] 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. 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.
[20] HSU C W, LIN C J. A Comparison of Methods for Multiclass Support Vector Machines[J]. IEEE Transactions on Neural Networks, 2002, 13(2): 415-425.
[21] 李慧, 王云鹏, 李岩, 等. 基于形态学和支持向量的遥感图像混合像元分解[J]. 遥感技术与应用, 2009, 24(1): 114-119. LI Hui, WANG Yunpeng, LI Yan, et al. Unmixing Remote Sensing Imagery Based on Morphology and Support Vector Machines[J]. Remote Sensing Technology and Application, 2009, 24(1): 114-119.
[22] TANG J, WANG L, MYINT S W. Improving Urban Classification Through Fuzzy Supervised Classification and Spectral Mixture Analysis[J]. International Journal of Remote Sensing, 2007, 28(18): 4047-4063.
[23] PONTIUS Jr R G, SHUSAS E, MCEACHERN M. Detecting Important Categorical Land Changes While Accounting for Persistence[J]. Agriculture, Ecosystems & Environment, 2004, 101(2-3): 251-268.
[24] WILLMOTT C J, MATSUURA K. On the Use of Dimensioned Measures of Error to Evaluate the Performance of Spatial Interpolators[J]. International Journal of Geographical Information Science, 2006, 20(1): 89-102.
[25] PONTIUS Jr R G, CHEUK M L. A Generalized Cross-tabulation Matrix to Compare Soft-classified Maps at Multiple Resolutions[J]. International Journal of Geographical Information Science, 2006, 20(1): 1-30.
[26] CHAPELLE O, VAPNIK V, BOUSQUET O, et al. Choosing Multiple Parameters for Support Vector Machines[J]. Machine Learning, 2002, 46(1-3): 131-159.
[27] 吴涛. 核函数的性质、方法及其在障碍检测中的应用[D]. 长沙: 国防科学技术大学, 2003. WU Tao. Kernels' Properties, Tricks and Its Applications on Obstacle Detection[D]. Changsha: National University of Defense Technology, 2003.