What options should I use to keep the pipeline synchronized with the input?

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson Xavier NX
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1.1
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) Questions
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I have a pipeline with a rtspsrc bin, bunch of video processing components including nvstreammux, and some other components for rtsp streamming.

Our task requires precision in timing and thus want to minimize the latency of the pipeline. A few (1-2) seconds are fine but we realize the latency keeps building up after letting the pipeline run for about 20 hours.

We understand there are unavoidable latency that we have to bear with given the number of video processing tasks and the processing power of the device, yet I believe there would be some properties or plugins that we can still use to minimize the latency.

Lowering the output resolution and/or including the interval in nvinfer also helps, but is there any way that we can force-set the maximum latency between the input and output stream? We wonder if any deepstream plugin has such property.

Just realized NvStreammux has max-latency property. I’ll close the issue!

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