Hello, I have a question and need your help

My system:
Ubuntu 20.04
Tesla T4
Driver: 470.47
CUDA 11.1
cuDNN 8.1
TensorRT 7.2
DeepStream SDK 5.1.0

I am currently using deepstream-test5 to run my yolov5. In deepstream-360d, multiple cameras can collaboratively predict the position of the vehicle. Based on this, I want to introduce this method into our program. However, I can only handle a single, and can’t work together. Can you help me?

Looking forward to your answer, thank you very much! ! !

Are you asking about multi camera input? you can refer to function create_multi_source_bin in sources/apps/apps-common/src/deepstream_source_bin.c