Multi Souce Question

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, , , ,
1

**• Hardware Platform (Jetson / GPU)**GPU
• DeepStream Version5.1
• TensorRT Version7.2.3
**• NVIDIA GPU Driver Version (valid for GPU only)**460.80
**• Issue Type( questions, new requirements, bugs)**questions

Hello, I wanna understand to inference question of multi source.

If I have a model, how can I inference multi source ?
I know I can add source config , I already used deepstram-app.
Therefore, I can add different postprocess rule?

I mean that if one of camera sources detects some objects, then I can know which source detect which objects?

I wanna to send command to it, bowever ,other source still don’t been effected.

Because I will deploy deepstream solution above thousands of customer sources. Please tell me how to solve that, it’s so important. Thank you.

3

**Before you start with deepstream, please make sure you are familiar with gstreamer knowledge and coding skills. ** GStreamer: open source multimedia framework

DeepStream is a SDK. deepstream-app is one of the sample applications to show how to use DeepStream APIs.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_C_Sample_Apps.html
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_ref_app_deepstream.html

The inference result is stored in deepstream Metadata.MetaData in the DeepStream SDK — DeepStream 6.3 Release documentation

In every FrameMeta, there is “source_id” which identify which stream(source) it belongs to. https://docs.nvidia.com/metropolis/deepstream/sdk-api/Meta/_NvDsFrameMeta.html