Tracker doesn't update

[Feraldkelo]

I am trying to use Bytetrack as my tracker, with detections coming from a custom-dataset-trained yolov5 model and it happens sometimes that some frame doesn't have any detection. In that case, the tracker fails to update. What could be some solution for that? Thank you in advance!

[github-actions[bot]]

👋 Hello @Feraldkelo, thank you for leaving an issue on Roboflow Notebooks.

🐞 Bug reports

If you are filing a bug report, please be as detailed as possible. This will help us more easily diagnose and resolve the problem you are facing. To learn more about contributing, check out our Contributing Guidelines.

If you require support with custom code that is not part of Roboflow Notebooks, please reach out on the Roboflow Forum or on the GitHub Discussions page associated with this repository.

💬 Get in touch

Do you have more questions about Roboflow that we haven't responded to yet? Feel free to ask them on the Roboflow Discuss forum. Our developer advocates and community team actively respond to questions there.

To ask questions about Notebooks, head over to the GitHub Discussions section of this repository.

[SkalskiP]

Hi, @Feraldkelo 👋🏻! As I understand it is not really a problem with our notebooks, so if that's okay with you I'll convert this issue into a discussion.

[Feraldkelo]

Hi @SkalskiP ! Yes, I am sorry for that! Actually, it is a problem that lies on the Bytetrack side. The update function of the BYTETracker class can't handle a case when the current frame doesn't have any detection. (when output_results = [ ] )
(P.S. Thank you for your work on these notebooks and the support.)

[SkalskiP]

No worries @Feraldkelo :) Working on this repository is a pure pleasure. The only problem is that I have other responsibilities at @roboflow and do not always have time to do everything.

As for your problem, I have an idea, but I'm not sure it works in your case. How about not updating the tracker in those situations? Simply if you have no detection don't update.