What could be the potential reasons for the obj_id range being limited to 0-65535 after adding the nvtracker plugin to deepstream in Python?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
jetson
• DeepStream Version
6.0
• JetPack Version (valid for Jetson only)
4.6.0
• TensorRT Version
8.0.1.6

my pipeline
uridecodebin-> streamux ->pgie->nvtracker->fakesink

nvtracker

ll_lib_file: /opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_nvmultiobjecttracker.so
  ll_config_file: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/config_tracker_NvDCF_perf.yml

“How should I modify the range of object_id in the probe function when adding a probe to the src pad of nvtracker? The current range is 0-65535.”

Object id in NvDsObjectMeta object from NvDCF tracker limited to int16 (0-65535)
3

The object_id is one counter internally. Why you need change the range?

4

I want to generate different object_ids within a day to distinguish between different objects, and I noticed that the object_id type is int32. Why does it start from 0 again after 66535

5

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. Maybe you can generate you own ID based on object_ids by yourself.

6

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