• Hardware Platform (Jetson / GPU) : Jetson
• DeepStream Version : 5.0 GA
• JetPack Version (valid for Jetson only) : 4.4
• TensorRT Version : 7.1.X
I’m working deepstream python app, and I want to use multi-stream RTSP object detection. My goal is to define ROI for each stream individually, and It’s possible to define src-crop and dest-crop in the property of nvvideoconvert element, but this is applied for all of streams, but I want to apply for each of stream individually.