L1/2正则化的逐次高光谱图像光谱解混

由于高光谱遥感图像的混合程度较高, 使得传统的非负矩阵欠逼近(Nonnegative Matrix Underapproximation, NMU)算法所提取的基本成分仍然“不纯”, 且易受噪声影响。针对这些不足, 提出了一种基于L1/2正则化的软阈值NMU逐次光谱解混算法。首先, 通过引入丰度的L1/2正则项来增强算法的地物区分能力, 进而提高所分离地物的纯度; 其次, 利用软阈值惩罚函数代替NMU中的残差非负约束, 通过调节惩罚因子来控制非负元素的数量, 从而提高算法的抗噪性能。在仿真数据和实测数据上的实验结果表明, 即使在有噪声的条件下, 该算法也能得到较好的分离结果。

Abstract

Due to the high mixed degree of hyperspectral remote sensing images, the basic component extracted by the traditional Nonnegative Matrix Underapproximation(NMU) algorithm is still "impurity", moreover, it is susceptible to noise. To overcome the above shortcomings, a method named L1/2-regularized soft-thresholding NMU for hyperspectral unmixing was proposed. Firstly, the L1/2 regularization term for abundance was introduced to improve the distinguishing ability, which can further improve the purity of the extracted components. Secondly, the soft-threshold penalty function was introduced to replace the residual nonnegative constraint in NMU. By adjusting the penalty factor, the number of non-negative elements could be well controlled, which could improve the anti-noise ability. Experimental results on the simulational and real datasets show that the proposed algorithm can obtain better separation results even under noisy conditions.

参考文献

[1] Chang C -I. Hyperspectral Data Processing: Algorithm Design and Analysis[M]. USA: John Wilely & Sons, 2013.

[2] Ma W K, Bioucas-Dias J M, Chan T H, et al. A signal processing perspective on hyperspectral unmixing: insights from remote sensing[J]. IEEE Signal Processing Magazine, 2014, 31(1): 67-81.

[3] Winter M E. N-FINDR: An algorithm for fast autonomous spectral endmember determination in hyperspectral data[C]// Proceedings of SPIE, 1999, 3753: 266-275.

[4] Nascimento J M P, Bioucas-Dias J M. Vertex component analysis: a fast algorithm to unmix hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(4): 898-910.

[5] Wang J, Chang C-I. Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(6): 1586-1600.

[6] Nascimento J M P, Bioucas-Dias J M. Hyperspectral unmixing based on mixtures of dirichlet components[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(3): 863-878.

[7] Iordache M D, Bioucas-Dias J M, Plaza A. Collaborative sparse regression for hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014,52(1): 341-354.

[8] Zhang S, Li J, Li H, et al. Spectral-spatial weighted sparse regression for hyperspectral image unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(6): 3265-3276.

[9] Feng X, Li H, Li J, et al. Hyperspectral unmixing using sparsity-constrained deep nonnegative matrix factorization with total variation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(10): 6245-6257.

[10] 魏一苇, 黄世奇, 王艺婷, 等. 基于体积和稀疏约束的高光谱混合像元分解算法[J]. 红外与激光工程, 2014, 43(4): 1247-1254.

Wei Yiwei, Huang Shiqi, Wang Yiting, et al. Volume and sparseness constrained algorithm for hyperspectral unmixing[J]. Infrared and Laser Engineering, 2014, 43(4): 1247-1254. (in Chinese)

[11] Tong L, Zhou J, Li X, et al. Region-based structure preserving nonnegative matrix factorization for hyperspectral unmixing[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(4): 1575-1588.

[12] Zhu F, Halimi A, Honeine P, et al. Correntropy maximization via ADMM: application to robust hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(9): 4944-4955.

[13] Gillis N, Plemmons R J. Sparse nonnegative matrix underapproximation and its application to hyperspectral image analysis[J]. Linear Algebra and Its Applications, 2013, 438(10): 3991-4007.

[14] Gillis, N, Glineur F. Using underapproximations for sparse nonnegative matrix factorization[J]. Pattern Recognition, 2010, 43(4): 1676-1687.

[15] Xu Z B, Zhang H, Wang Y, et al. L1/2 regularization[J]. Science China Information Sciences, 2010, 53(6): 1159-1169.

[16] Boyd S, Parikh N, Chu E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J]. Foundations and Trends in Machine Learning, 2010, 3(1): 1-122.

[17] Xu Z B, Chang X Y, Xu F M, et al. L1/2 regularization: a thresholding representation theory and a fast solver[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(7): 1013-1027.

[18] Guo Z H, Wittman T, Osher S. L1 unmixing and its application to hyperspectral image enhancement[C]// Proceedings of SPIE, 2009, 7334: 1-9.

汤毅, 粘永健, 何密, 王倩楠, 许可. L1/2正则化的逐次高光谱图像光谱解混[J]. 红外与激光工程, 2019, 48(7): 0726003. Tang Yi, Nian Yongjian, He Mi, Wang Qiannan, Xu Ke. Successive spectral unmixing for hyperspectral images based on L1/2 regularization[J]. Infrared and Laser Engineering, 2019, 48(7): 0726003.

L1/2正则化的逐次高光谱图像光谱解混

关于本站 Cookie 的使用提示

全站搜索

L1/2正则化的逐次高光谱图像光谱解混

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索