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

evaluation code #3

Open
pribadihcr opened this issue Sep 28, 2016 · 3 comments
Open

evaluation code #3

pribadihcr opened this issue Sep 28, 2016 · 3 comments

Comments

@pribadihcr
Copy link

Hi @HyeonseobNam

is there a code for measuring the accuracy and robutsness of the tracker ?. Thanks.

@hyseob
Copy link
Owner

hyseob commented Sep 28, 2016

Hi, @pribadihcr
You can measure the accuracy and robustness using the VOT toolkit: http://www.votchallenge.net/howto/
Thank you.

@pribadihcr
Copy link
Author

Hi @HyeonseobNam,

So, for example, to measure the accuracy, using the following function:
function [accuracy, frames] = estimate_accuracy(trajectory, sequence, varargin)

The trajectory is bounding box of the tracker's result and the sequence is the ground truth right?.

Thanks.

@hyseob
Copy link
Owner

hyseob commented Sep 28, 2016

@pribadihcr
The accuracy and robustness (by the VOT definition) are not simply obtained from a single-run trajectory.
You need to re-initialize the tracker at each tracking failure to get the trajectory following the VOT protocol.
Then the accuracy is the overlapping ratio between the trajectory and the ground-truth, and the robustness is the number of failures.
I believe the guideline at the VOT website would be much helpful.

Thanks.

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

2 participants