DeepSORT on DeepStream 6.0

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU): jetson
**• DeepStream Version: 6.0
**• JetPack Version (valid for Jetson only): 4.6
**• Issue Type( questions, new requirements, bugs): questions

I would like to use DeepSORT with the NvMultiObjectTracker library.

Referring to its document, DeepSORT algorithm on DeepStream use Re-ID similarity and proximity to filter a set of candidate detector objects for each target tracker.
Then only Re-ID similarity is used to find best match of each target and its candidate detector objects.

I would like to know if boundig box size and location are also used during the match algorithm or not because the parametes can be set in .yml file.

And besides, do you open the source code of NvMultiObjectTracker?
I want to understand DeepSORT algorithm on DeepStream in more detail.

Thank you.

We haven’t plan to open source tracker. Please check the document:

Gst-nvtracker — DeepStream 6.1 Release documentation (nvidia.com)

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Yes, data association will use those information.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.