I found that for my system, the covariance matrix was growing like crazy (P_k~10^8*P_k-1) and was getting complex.
Try adjusting the alpha parameter. 10e-3 was way too small for my system, and 0.1 was the bare minimum that I could avoid the covariance issues. 0.15 seemed to work best.
in general, alpha is recommended to be between 10e-3 and 1.
There is no productive 2D example provided that show the superiority of this method over regular gaussian smoothing. A simple combination of Gaussian and Median filtering provides better denoising than what is proposed:
s = phantom(512) + randn(512);
num_iter = 55;
delta_t = 1/7;
kappa = 30;
option = 2;
ad = anisodiff2D(s,num_iter,delta_t,kappa,option);
It is very likely that the authors generalization of using 8 point neighbourhoods is valid, but if so it changes the valid range of the parameters, and thus one cant easily recreate the results of the original Perona-Malik paper. If a simple example was provided that showed how the 2D method actually outperforms gaussian blurring, then I might be inclined to read the secondary paper referenced.
the interpretation of the kappa parameter is nicely given in weickerts book: http://www.lpi.tel.uva.es/muitic/pim/docus/anisotropic_diffusion.pdf, chapter 1, figure 1.1, b... (its called lambda there)
I cant get that interpretation to work for me here. Whats wrong? How can i strengthen the edges in the image using this, while blurring along isolines!?
Again, if only a positive example was provided for the 2D case, this might all be cleared up.
I really have not understood this code yet. In my case, I also study on EKF for GPS data that I want to apply EKF to due with noise and missing data in GPS data. I have one GPS data columm with more than 2000 of length. Who could show me how to do it?
Thank you so much for your kinds