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

Feature Request: Linking Tracklets to Trajectories #109

Open
jokober opened this issue Oct 27, 2022 · 1 comment
Open

Feature Request: Linking Tracklets to Trajectories #109

jokober opened this issue Oct 27, 2022 · 1 comment

Comments

@jokober
Copy link

jokober commented Oct 27, 2022

Not sure how much features you want to integrate into yupi but I thought it would be really great to have general tracklet linking features in order to connect tracklets created due to id switches while tracking.

Thanks for all your work on yupi!

@gvieralopez
Copy link
Member

gvieralopez commented Oct 27, 2022

Dear jokober. Thank you for your interest and your kind words.

We have designed yupi in such a way that extracting tracklets from yupi trajectories can be easily achieved via python indexing:

tracklet = traj[50:100]

Where tracklet will be also a yupi.Trajectory object. Then, you could extract the same kind of features you get from the full-length trajectory.

EDIT: Now, I realize we don´t have a way to concatenate two trajectories into one. That is probably what you are asking for. In that case, I am wondering if it should be better to provide a simple concatenation operator, so we could do something like:

traj = tracklet1 >> tracklet2

In this case, the user should take care of both tracklets being 'continuous'. Maybe, most of the time the user will be forced to do something like:

tracklet2 = tracklet2 - tracklet2.r[0] + tracklet1.r[-1]

before using the concatenation operator.

Or even forcing some rotation to preserve the direction of the final steps of the first tracklet.

Do you think a simple concatenation should be fine, or we should include a 'smarter' concatenation function with all these considerations.

I am not sure if I am fully answering your question. Feel free to point us to any specific direction we could be missing here.

If you want to, you could also join our yupi discussion group in Telegram, where we can discuss implementation details:
https://t.me/yupi_discuss

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