Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Faster version (Dual Correlation Filter - DCF) #1

Open
cory8249 opened this issue Nov 18, 2016 · 3 comments
Open

Faster version (Dual Correlation Filter - DCF) #1

cory8249 opened this issue Nov 18, 2016 · 3 comments

Comments

@cory8249
Copy link

Hi, thank you for sharing this awesome python implementation.

Can you please implement the DCF function in python?
In the paper, the author clams that DCF is 70% faster than KCF, with only little accuracy lose.

The original matlab code does implement both KCF & DCF
http://www.robots.ox.ac.uk/~joao/circulant/

It seems that there is only slightly changes between 2 correlation functions.

image

image

@drord9
Copy link

drord9 commented Nov 20, 2016

hi,
joining to the request.
Thanks.

@uoip
Copy link
Owner

uoip commented Nov 21, 2016

Hello, thanks for your comments. These days I'm busy with my own work(some NLP tasks), so don't have much time to review the code, for now, if you just want a faster version, you can try KCFcpp-py-wrapper, it's faster than this pure python implementation. I may look into the matlab code later, and you can also implement this function yourself, rewriting code is a good way to learn.

@wjtan99
Copy link

wjtan99 commented Apr 7, 2018

Is dual CF same as linear KCF?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants