Tracker module rewrite problem

If my tracker wants to access bytetrack, how should I rewrite the tracker? At the same time, I want to know that the reasoning comes out to track here. Like deepsort, it does have a Kalman filter operation, but I found that the current open source solutions on GitHub are all based on the CPU side. What I want to ask is, how to build a GPU based pipeline?

In addition, I would like to know what mature solutions are there for this idea? Although I don’t know much about pipelines

• Hardware Platform (Jetson / GPU) :GPU
• DeepStream Version :6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only) :nvidia-480
• Issue Type( questions, new requirements, bugs) :questions or bugs
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Please follow the guide to implement custom low level tracker: Gst-nvtracker — DeepStream 6.2 Release documentation

Can you please provide some sample code for implementing the custom low level library.

1 Like

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