Abstract：Aiming at the problem that hyperspectral unmixing based on Non-negative Matrix Factorization (NMF) is easy to fall into local minimum and greatly affected by initial value, a linear unmixing algorithm based on Sparse and Orthogonal constrained Non-negative Matrix Factorization (SONMF) was proposed. Firstly, based on the traditional NMF hyperspectral linear unmixing method, the physical and chemical properties of the hyperspectral data was analyzed. Then the sparsity of the abundance and the independence of the endmember were combined together, two methods of Sparse Non-negative Matrix Factorization (SNMF) and Orthogonal Non-negative Matrix Factorization (ONMF) were combined and applied into hyperspectral unmixing. The experiments on simulation data and real data show that, compared with the three reference unmixing algorithms of Vertex Component Analysis (VCA), SNMF and ONMF, the proposed algorithm has improved the performance of linear unmixing, in which the Spectral Angle Distance (SAD) is reduced by 0.012 to 0.145. SONMF can combine the advantages of the two constraints to make up for the lack the expression of hyperspectral data by traditional NMF based linear unmixing methods, and achieve good results.
[1] 童庆禧,张兵,郑兰芬.高光谱遥感——原理、技术与应用[M].北京:高等教育出版社, 2006:15-30. (TONG Q X, ZAHNG B, ZHENG L F. Hyperspectral Remote Sensing——Principle, Technology and Application[M]. Beijing:Higher Education Press, 2006:15-30.) [2] BIOUCAS-DIAS J M, PLAZA A, DOBIGEON N, et al. Hyperspectral unmixing overview:geometrical, statistical, and sparse regression-based approaches[C]//Proceedings of the 2011 IEEE International Geoscience and Remote Sensing Symposium. Piscataway, NJ:IEEE, 2011:1135-1138. [3] 张兵,孙旭.高光谱图像混合像元分解[M].北京:科学出版社, 2015:6-22. (ZAHNG B, SUN X. Hyperspectral Image Unmixing[M]. Beijing:Science Press, 2015:6-22.) [4] LEE D D, SEUNG S S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401:788-791. [5] 袁博.马尔可夫随机场的空间相关模型在非负矩阵分解线性解混中的应用[J].计算机应用,2017,37(12):3563-3568. (YUAN B. Application of MRF's spatial correlation model in NMF-based linear unmixing[J]. Journal of Computer Applications, 2017, 37(12):3563-3568.) [6] 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. [7] RAJABI R, GHASSEMIAN H. Spectral unmixing of hyperspectral imagery using multilayer NMF[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 12(1):38-42. [8] ZHAO Y, ZHOU Z, WANG D, et al. Hyperspectral image unmixing algorithm based on endmember-constrained nonnegative matrix factorization[J]. Frontiers of Optoelectronics, 2016, 9(4):627-632. [9] QIAN Y, JIA S, ZHOU J, et al. Hyperspectral unmixing via L1/2 sparsity-constrained nonnegative matrix factorization[J]. IEEE Transactions on Geoscience & Remote Sensing, 2011, 49(11):4282-4297. [10] 余肖玲.非负矩阵分解理论及其在高光谱解混中的应用[D]. 成都:成都理工大学, 2015:45-60. (YU X L. The theory of Nonnegative matrix factorization and its application in the hyperspectral unmixing[D]. Chengdu:Chengdu University of Technology, 2015:45-60.) [11] NASCIMENTO J M P,BIOOUCASDIAS J M B. Vertex component analysis:a fast algorithm to unmix hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(4):898-910. [12] HEINZ D C, CHANG C. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 39(3):529-545. [13] POMPILI F, GILLIS N, ABSIL P, et al. Two algorithms for orthogonal nonnegative matrix factorization with application to clustering[J]. Neurocomputing, 2014, 141:15-25. [14] 李孟杰,谢强,丁秋林.基于正交非负矩阵分解的K-means聚类算法研究[J].计算机科学,2016,43(5):204-208. (LI M J, XIE Q, DING Q L. Orthogonal Non-negative Matrix Factorization for K-means Clustering[J]. Computer Science, 2016, 43(5):204-208.) [15] BIOUCASDIAS J M, NASCIMENTO J M P. Hyperspectral subspace identification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(8):2435-2445. CHEN Shanxue, born in 1966, Ph.D., professor. His research interests including image processing, data compression.CHU Chengquan, born in 1993, M.S. candidate. His research interests including hyperspectral image unmixing.
2019, Vol. 39 
