What is the reasoning behind dividing sigma by 2.5 when performing edge validation?

Open MrZander opened this issue 3 years ago • 0 comments

The paper states that ED works best with sigma = 1, which I can see is what is used. But, why then does the code divide the original sigma by 2.5 and re-smooth the image? https://github.com/CihanTopal/ED_Lib/blob/6ea56f18bb0409736ca569d139750ff0685a7ec5/EDPF.cpp#L20

I don't see any rational for this in the paper, am I missing something? Does this produce better validation results?

Oct 17 '22 23:10 MrZander