How can I construct the multi-sources-vs-multi-models stream?

[1102696569]

Multiple rtsp sources will  compute with multiple algrithm models.  The  relation between them is multi-vs-multi.  Is there any reference examples or  solution? 
 Appreciate for your replies!

[DaneLLL]

Hi,
You can refer to

Adding a ghost pad after splitting a pipeline using Tee?

Hi, One possible solution is to link two nvinfer in series such as: $ gst-launch-1.0 uridecodebin uri=file:///home/nvidia/1080.mp4 ! mx.sink_0 nvstreammux width=1920 height=1080 batch-size=1 name=mx ! nvinfer config-file-path=/home/nvidia/deepstream-4.0/samples/configs/deepstream-app/config_infer_primary_nano.txt unique-id=7 ! nvinfer config-file-path=/home/nvidia/deepstream-4.0/samples/configs/deepstream-app/config_infer_primary.txt unique-id=8 ! nvvideoconvert ! nvdsosd ! nvoverlaysink You …

[1102696569]

This way is not sufficient to multi-vs-multi relation. I have find a solution. Every rtsp constructs a pipeline . And every model constructs a pipeliine. Then rtsp pipelines and model pipelines are linked by “appsink” elements pushing buffer to “appsrc” elements.