Different objects receive the same tracker id

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1.1
• TensorRT Version 8.5.2.2
• Issue Type( questions, new requirements, bugs) Questions

Using the nvdanalytics example and the NvDCF tracker, with the same configuration as the example, I have a problem. Two different objects get the same ID. The problem occurs if in the image in the lower left corner an object goes out of the field of view and another object enters again more or less in the same part of the image, although they are different objects. How can I vary my config_tracker_NvDCF_perf.yml so that once an object goes out of the image it doesn’t assign the same id to a new object?

image

image

3

Can you have a try with: /opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/config_tracker_NvDCF_accuracy.yml ?

4

Thanks, I just tried it, but it still detects the second person as person 1. I have the feeling that the ids are unique in each frame, but maybe they should increase with each person that appears in the image, can’t this behaviour be forced?

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

Can you share your test video and reproduce steps? So we can have a check.

7

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