文章详情

摘要

为了解决传统高光谱图像解混方法中存在的解混效率低、计算复杂和易受噪声和异常点影响等问题，提出了一种基于L1/2稀疏性和峰度平滑约束非负矩阵分解（L1/2-KSNMF）的算法。针对高光谱图像中非线性混合情形，该方法首先引入了L1/2范数作为稀疏度度量，提高解混的准确性；引入峰度平滑约束，将空间信息融合到解混模型中，提高解混结果的空间连续性；实验结果表明，该算法在解混准确性和计算效率以及从高光谱数据中提取端元光谱方面都表现出优异的性能。

关键词

高光谱图像；非负矩阵分解；L1/2稀疏约束；高光谱图像解混（HU）

参考文献

1. [1] KHAN M J，KHAN H S，YOUSAF A，et al. Modern Trends in Hyperspectral Image Analysis: A Review [J].IEEE Access，2018，6：14118–14129.
2. [2] NASCIMENTO J M，BIOUCAS-DIAS J M. Blind Hyperspectral Unmixing [C]//Image and Signal Processing for Remote Sensing XIII. San Diego：SPIE，2007：12-23.
3. [3] BHATT J S，JOSHI M V. Deep Learning in Hyperspectral Unmixing: A Review [C]//IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. Waikoloa：IEEE，2020：1-5.
4. [4] LU X Q，WU H，YUAN Y，et al. Manifold Regularized Sparse NMF for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2012，51（5）：2815-2826.
5. [5] LIU Y，GUO Y，LI F，et al. Sparse Dictionary Learning for Blind Hyperspectral Unmixing [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2018，16（4）：578-582.
6. [6] TONG L，ZHOU J，QIAN B，et al. Adaptive Graph Regularized Multilayer Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，13：434-447.
7. [7] PENG J，ZHOU Y，SUN W，et al. Self-Paced Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2020，59（2）：1501-1515.
8. [8] HAN H，WANG G，WANG M，et al. Hyperspectral Unmixing via Nonconvex Sparse and Low-Rank Constraint [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2020，13：5704-5718.
9. [9] ZHANG S，ZHANG G，LI F，et al. Spectral-Spatial Hyperspectral Unmixing Using Nonnegative Matrix Factorization [J].IEEE Transactions on Geoscience and Remote Sensing，2021，60：1-13.
10. [10] EKANAYAKE E，WEERASOORIYA H，RANASINGHE D Y L，et al. Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing Incorporating Endmember Independence [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2021，14：11853-11869.
11. [11] BURRED J J. Detailed Derivation of Multiplicative Update Rules for NMF [EB/OL].（2024-06-25）.https://www.jjburred.com/research/pdf/jjburred_nmf_updates.pdf.
12. [12] PASCUAL-MONTANO A，CARAZO J M，KOCHI K，et al. Nonsmooth Nonnegative Matrix Factorization (nsNMF) [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2006，28（3）：403-415.
13. [13] LEE D，SEUNG H. Algorithms for Non-Negative Matrix Factorization [C]//Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS).Vancouver：NIPS，2001：535-541.
14. [14] SHI C，WANG L. Linear Spatial Spectral Mixture Model [J].IEEE Transactions on Geoscience and Remote Sensing，2016，54（6）：3599-3611.
15. [15] QIAN Y，JIA S，ZHOU J，et al. Hyperspectral Unmixing via L1/2 Sparsity-Constrained Nonnegative Matrix Factorization [J].IEEE Transactions on Geoscience and Remote Sensing，2011，49（11）：4282-4297.
16. [16] WANG X，ZHONG Y，ZHANG L，et al. Spatial Group Sparsity Regularized Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2017，55（11）：6287-6304.
17. [17] LEPALT V，ANG A M S，GILLIS N. Minimum-Volume Rank-Deficient Nonnegative Matrix Factorizations [C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Brighton：IEEE，2019：3402-3406.
18. [18] LI J，BIOUCAS-DIAS J M，PLAZA A，et al. Robust Collaborative Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Transactions on Geoscience and Remote Sensing，2016，54（10）：6076-6090.

基金项目

江西省教育厅科技计划项目（GJJ210861）；江西省教育厅科技项目（GJJ200879）

作者简介

杨国亮（1973—），男，汉族，江西宜春人，教授，博士，研究方向：人工智能与模式识别；通信作者：张佳琦（2000—），男，汉族，江西宜春人，硕士研究生在读，研究方向：深度学习与模式识别；盛杨杨（1997—），男，汉族，江苏扬州人，硕士研究生在读，研究方向：深度学习与模式识别。