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

Is there a way to do the multi-class multi-object tracking #41

Open
mehdiiranmanesh opened this issue Sep 15, 2021 · 1 comment
Open
Labels
enhancement New feature or request

Comments

@mehdiiranmanesh
Copy link

mehdiiranmanesh commented Sep 15, 2021

Thank you for your great work. Does this algorithm and repo support multi-class as well?

@noahcao
Copy link

noahcao commented Oct 11, 2021

We didn't make that as we originally target for the pedestrian-only tracking datasets, i.e. MOT datasets. But that might be trivial to support with minor modification:

  1. Following the DETR or Deformable DETR logic, we should more category for the classification.
  2. For the matching part, apart from the current matching cost, we should make sure the category is kept for the objects to be associated.
    But all these require you to train the model on corresponding datasets. We may make such support in the future.

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

No branches or pull requests

3 participants