search

joaofaro / KCFcpp

C++ Implementation of KCF Tracker
BSD 3-Clause "New" or "Revised" License
895 stars 446 forks source link

Some questions about the circshift in the code(the Matlab version)? #3

Closed Happyjie1993 closed 8 years ago

Happyjie1993 commented 8 years ago

Thanks a lot for your open source, you are really a kind man. Recently, I have read your two papers, "Exploiting the Circulant Structure of Tracking-by-detection with Kernels" and "High-Speed Tracking with Kernelized Correlation Filters", and I download your codes (Matlab version) from the hyperlink given by the "Visual Tracker Benchmark", it's really very useful for me, a novice, to get further understanding about the KCF algorithm. Unfortunately, there are still some questions for me to understanding the algorithm and the codes, that I don't understand the dense sampling and the usefulness of the command 'circshift' in your "Code Version 1", the "dense_gauss_kernel.m" more specifically, xy = real(circshift(ifft2(xyf), floor(size(x)/2))); %to spatial domain http://www.robots.ox.ac.uk/~joao/circulant/index.html(I get your code from this url, Matlab code — version 1)

So I wish to get some instructions from you to help me understand this problem better.I would appreciate it very much if i can obtain any support from you.

joaofaro commented 8 years ago

Hi!

I am sorry for the late reply. I am not the author of the algorithm (and the Matlab version of it), I just implemented a C++ version of it. The author's name is João Filipe Henriques, I think you can find his personal email on his page, I advise you to send him an email with your questions (he is a really nice guy!).

Good luck on your work.

Best regards, João Faro

On 27 March 2016 at 16:09, Happyjie1993 notifications@github.com wrote:

Thanks a lot for your open source, you are really a kind man. Recently, I have read your two papers, "Exploiting the Circulant Structure of Tracking-by-detection with Kernels" and "High-Speed Tracking with Kernelized Correlation Filters", and I download your codes (Matlab version) from the hyperlink given by the "Visual Tracker Benchmark", it's really very useful for me, a novice, to get further understanding about the KCF algorithm. Unfortunately, there are still some questions for me to understanding the algorithm and the codes, that I don't understand the dense sampling and the usefulness of the command 'circshift' in your "Code Version 1", the "dense_gauss_kernel.m" more specifically, xy = real(circshift(ifft2(xyf), floor(size(x)/2))); %to spatial domain http://www.robots.ox.ac.uk/~joao/circulant/index.html http://url(I get your code from this url, Matlab code — version 1)

So I wish to get some instructions from you to help me understand this problem better.I would appreciate it very much if i can obtain any support from you.

— You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub https://github.com/joaofaro/KCFcpp/issues/3

Happyjie1993 commented 8 years ago

Thank you so much and I have sent an email (several emails actually) to João Filipe Henriques, but I'm not sure he receives it since a failure appeared in every time sending.

I'm sorry that I have mixed you two up~~

Thank you~~~

joaofaro commented 8 years ago

Hi again,

No problem, the first name and the initial letter of the last name are the same, I think it's normal :)

He changed from the ISR-University of Coimbra to Oxford. Maybe his ISR email is not working anymore or his new Oxford email is not fully working (I don't know, I'm just trying to guess). Have you tried both emails?

On 29 March 2016 at 15:09, Happyjie1993 notifications@github.com wrote:

Thank you so much and I have sent an email (several emails actually) to João Filipe Henriques, but I'm not sure he receives it since a failure appeared in every time sending.

I'm sorry that I have mixed you two up~~

Thank you~~~

— You are receiving this because you commented. Reply to this email directly or view it on GitHub https://github.com/joaofaro/KCFcpp/issues/3#issuecomment-202884307

Happyjie1993 commented 8 years ago

Hi~ I guess I sent the email to his new mailbox since the suffix of the mailbox adress is '@robots.ox.ac.uk'. And I have changed my mailbox and sent again, getting the same result unfortunately.I don't the konw the reason. Then I get his old mailbox adress in the paper, and send once again. It seems everything is going OK since no failure appeared. Maybe it woks ~

I want to say thank you from my botton of my heart. You are really a nice man~~

joaofaro commented 8 years ago

Thank you! And no worries, mine is too far from being perfect either ;) I hope you can contact him. Good luck on your work!

On 29 March 2016 at 15:54, Happyjie1993 notifications@github.com wrote:

Hi~ I guess I sent the email to his new mailbox since the suffix of the mailbox adress is '@robots.ox.ac.uk'. And I have changed my mailbox and sent again, getting the same result unfortunately.I don't the konw the reason. Then I get his old mailbox adress in the paper, and send once again. It seems everything is going OK since no failure appeared. Maybe it woks ~

I want to say thank you from my botton of my heart. You are really a nice man(Sorry about my poor English)

— You are receiving this because you commented. Reply to this email directly or view it on GitHub https://github.com/joaofaro/KCFcpp/issues/3#issuecomment-202904429