A comparison of kernel functions for intimate mixture models

Nonlinear Unmixing of Hyperspectral Data Based on a Linear-Mixture/Nonlinear-Fluctuation Model

“…The cost function can be directly reformulated as a function of . The two constraints over become Eliminating the second constraint, which is trivial because of the first constraint, leads us to (31) and (32). Because and , we have with .…”

Modeling linear and intimate mixtures of materials in hyperspectral imagery with single-scattering albedo and kernel approaches

“…A physics-inspired kernel was proposed and shown to provide significantly improved behavior to model nonlinear mixtures, but a result of that effort was that although each kernel provides good results for the type of mixing intended, only one kernel or the other could be used, for either linear mixtures or intimate mixtures, but not both. 36 The kernel approach was further developed by Broadwater and Banerjee 37,38 into a generalized method for adaptive linear and intimate mixtures. This method is motivated by attempting to simulate Hapke theory for SSA by making use of the kernel E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 1 2 ; 1 1 6 ; 3 6 7…”

“…[32][33][34][35][36][37][38][39] Kernel functions provide a way to generalize linear algorithms to nonlinear data. 32,33 In the cases of detection and classification applications, they can induce high-dimensional feature spaces.…”

Martian aerosol abundance estimation based on unmixing of hyperspectral imagery

“…More complicated approaches are needed. In [2], it is proposed to use the kernel models in order to quantify the chemical species which are intimately mixed. In addition, the surface reflectance is transmitted by the atmosphere and the aerosol.…”