19 January 2016 Nonlinear hyperspectral unmixing based on sparse non-negative matrix factorization
Author Affiliations +
J. of Applied Remote Sensing, 10(1), 015003 (2016). doi:10.1117/1.JRS.10.015003
Hyperspectral unmixing aims at extracting pure material spectra, accompanied by their corresponding proportions, from a mixed pixel. Owing to modeling more accurate distribution of real material, nonlinear mixing models (non-LMM) are usually considered to hold better performance than LMMs in complicated scenarios. In the past years, numerous nonlinear models have been successfully applied to hyperspectral unmixing. However, most non-LMMs only think of sum-to-one constraint or positivity constraint while the widespread sparsity among real materials mixing is the very factor that cannot be ignored. That is, for non-LMMs, a pixel is usually composed of a few spectral signatures of different materials from all the pure pixel set. Thus, in this paper, a smooth sparsity constraint is incorporated into the state-of-the-art Fan nonlinear model to exploit the sparsity feature in nonlinear model and use it to enhance the unmixing performance. This sparsity-constrained Fan model is solved with the non-negative matrix factorization. The algorithm was implemented on synthetic and real hyperspectral data and presented its advantage over those competing algorithms in the experiments.
© 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)
Jing Li, Xiaorun Li, Liaoying Zhao, "Nonlinear hyperspectral unmixing based on sparse non-negative matrix factorization," Journal of Applied Remote Sensing 10(1), 015003 (19 January 2016). https://doi.org/10.1117/1.JRS.10.015003

Fluctuations and noise


Signal to noise ratio


Data modeling


Performance modeling

Back to Top