Why do you save frames with Nvmultisteamtiler probes?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

• Hardware Platform (Jetson / GPU) Jetson Xavier NX
• DeepStream Version 6.0.1
• JetPack Version (valid for Jetson only) 4.6.1
• TensorRT Version 8.2.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
Hi ,
I have a sample application [deepstream_imagedata-multistream.py](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/blob/master/apps/deepstream- imagedata-multistream/deepstream_imagedata-multistream.py).
I was able to have rtsp input 4 video frames and save each frame.
So I had one question.
Q: This sample app is performing the frame saving process within the Nvmultistreamtiler probe. There is also an Nvdsosd element in the pipeline, can’t we do frame saving here?

3

Yes, you can add the probe to the nvdsosd plugin.

4

So instead of stopping storing frames in the nvmultistreamtiler probe, can I add a new nvdsosd probe and store frames in the nvdosd probe?

5

Yes, you can. But if you want to get the frames with bbox, you need to add that to the src pad of nvdsosd or the sink pad of nvmultistreamtiler.

6

Yes, sir. Thank you for the reference. Thank you very much.

7

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