Hey folks, can you temme if its perfectly usable to simulate a SAR image by pasting the SAR pattern of a flat roofed building on a gray background to generate multiple images to test a change detection algorithm.
Do you know of any such codes, Plzzzzzzzz inform me!
Thanks for the code it was very helpful. However, I want to compare two images using MI. If I do it pixel by pixel using the given code, I mostly get a warning: divide by zero and receive a value NaN for MI. Now I can try and work with very small windows also but that would seem to reduce the quality of my results. Is there another way or by enhancing this code somehow to analyse the two images together almost pixelwise.
Is there any assumption made when calculating mutualinfo(x, y) if one of vector x,y is binary?
In my data, y is binary and I tried several different x. Surprisingly, several different x give the same mutualinfo to the last digit of double type.
I think some assumption must be made on estimating kernel density. Could author give some insight?
There are a couple of assumptions that can change the end result. One is that the histogram has one tail longer than the other and that the threshold has to be on the long tail side. The other is the definition of the end point of a histogram tail. In the code, this is set to 10000 (i.e. tails end when there are less than 10000 pixels in the corresponding histogram bin). Depending on the size of the image, this might not be an optimum choice.