Integration of Kafka with a DeepStream Python Pipeline for Multiple Input and Output Sources and Cropping Image

• Hardware Platform (Jetson / GPU): dPU A40.
• DeepStream Version: 6.4-triton-multiarch.
• TensorRT Version: 8.6.2.3.
• NVIDIA GPU Driver Version (valid for GPU only): 525.147.05.
• Issue Type( questions, new requirements, bugs): questions.
• 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)

I am currently using DeepStream Python to develop a pipeline for multiple input sources and multiple RTSP output sources, and I have completed this setup. Now, I want to integrate Kafka using msgconv and msgbroker . How should I design the pipeline considering that after the demux , each input source will have a separate branch? Where should I place msgconv and msgbroker - in each branch or elsewhere? Also, if I want to extract images from the buffer for object cropping, at which element should I place the probe? I tried it at sgie , but it reported an error, only supporting the RGBA format? Thank you in advance.

please refer to this topic.

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