You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi~~
Thanks for you open source. It's very useful for me to get further understand of the KCF algorithm. Unfortunately, there are still some questions for me to understanding the algorithm and the codes. I don't understand the dense sampling process essentially. It seems there are no relevant codes in your project to get the circulant matrice as says in the paper. In adition, I can't figure out the usefulness of the command 'circshift' in gaussian_shaped_labels.m: %move the peak to the top-left, with wrap-around labels = circshift(labels, -floor(sz(1:2) / 2) + 1);
It's great that your codes have so many annotations, but I don't understand the annotation 'move the peak to the top-left, wiht warp-around'. So, could you explain it in more detail for me? I would be very appreciated if I can get any hints from you.
Best regards,
Jie
The text was updated successfully, but these errors were encountered:
Hi~~
Thanks for you open source. It's very useful for me to get further understand of the KCF algorithm. Unfortunately, there are still some questions for me to understanding the algorithm and the codes. I don't understand the dense sampling process essentially. It seems there are no relevant codes in your project to get the circulant matrice as says in the paper. In adition, I can't figure out the usefulness of the command 'circshift' in gaussian_shaped_labels.m:
%move the peak to the top-left, with wrap-around labels = circshift(labels, -floor(sz(1:2) / 2) + 1);
It's great that your codes have so many annotations, but I don't understand the annotation 'move the peak to the top-left, wiht warp-around'. So, could you explain it in more detail for me? I would be very appreciated if I can get any hints from you.
Best regards,
Jie
The text was updated successfully, but these errors were encountered: