Hyperspectral image unmixing algorithm based on endmember-constrained nonnegative matrix factorization  

作　　者：Yan ZHAO Zhen ZHOU Donghui WANG Yicheng HUANG Minghua YU 

机构地区：[1]School of Measurement and Communication, Harbin University of Science and Technology, Harbin 150080, China [2]School of Electrical and Control Engineering, Heilong~iang University of Science and Technology, Harbin 150022, China [3]College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China [4]Qiqihar Vehicle G-roup.Qiqihar 161000, China

出　　处：《Frontiers of Optoelectronics》2016年第4期627-632,共6页光电子前沿（英文版）

摘　　要：The objective function of classical nonnegative matrix factorization （NMF） is non-convexity, which affects the obtaining of optimal solutions. In this paper, we proposed a NMF algorithm, and this algorithm was based on the constraint of endmember spectral correlation minimization and endmember spectral difference max- imization. The size of endrnember spectral overall- correlation was measured by the correlation function, and correlation function was defined as the sum of the absolute values of every two correlation coefficient between the spectra. In the difference constraint of the endmember spectra, the mutation of matrix trace was slowed down by introducing the natural logarithm function. Combining the image decomposition error with the influences of end- member spectra, in the objective function the projection gradient was used to achieve NMF. The effectiveness of algorithm was verified by the simulated hyperspeetral images and real hyperspectral images.The objective function of classical nonnegative matrix factorization （NMF） is non-convexity, which affects the obtaining of optimal solutions. In this paper, we proposed a NMF algorithm, and this algorithm was based on the constraint of endmember spectral correlation minimization and endmember spectral difference max- imization. The size of endrnember spectral overall- correlation was measured by the correlation function, and correlation function was defined as the sum of the absolute values of every two correlation coefficient between the spectra. In the difference constraint of the endmember spectra, the mutation of matrix trace was slowed down by introducing the natural logarithm function. Combining the image decomposition error with the influences of end- member spectra, in the objective function the projection gradient was used to achieve NMF. The effectiveness of algorithm was verified by the simulated hyperspeetral images and real hyperspectral images.

关 键 词：hyperspeclral image UNMIXING nonnegativematrix factorization （NMF） correlation logarithm function 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]