Use Multi-stream decoded frames of deep-stream-python-apps in custom code

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

• Hardware Platform Jetson nano
• DeepStream Version 5.0 DP
• JetPack Version (valid for Jetson only) 4.4 DP
• TensorRT Version 7.X

I want to use deepstream-python-apps for decoding the rtsp multi-stream and then I want to use the decoded frames in my custom application python, How do I do,? I want to put the frame_image into queue but this don’t work, How do I can use the decoded frames in custom python code?

5

What does "put the frame_image into queue"mean? What will you do to the decoded frames?

6

I want to passed the decoded frames as numpy array into custom processing unit.

7

Will the frames be back into the deepstream pipeline after processing? If not, you may refer to the sample codes of deepstream-imagedata-multistream, it will get the decoded frames from the pipeline and save them as pictures.