Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) Xavier NX
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only) 4.6
• TensorRT Version 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• 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)
General question about nv-streammux and ntp timestamps. I have a pipeline that simplified looks like this
RTSP source > nvstreammux > queue > PGIE > SQIE > Fakesink
The SGIE is a heavy model, and introduces latency in the pipeline when its processing causing frames to queue up. Thats theoretically not a problem as I rely on the NTP timestamp from nvstreammux for further processing in a probe. However, I have observed some irregularities when there is concurrent heavy load on SGIE.
In your documentation for ntp timestamps (link below) it clearly states that the ntp timestamp when using the host system ntp synchronized time, is set when the frame is received by nvstreammmux.
My first question is: Can frames queue up in nv-streammux (Before its considered received)?
My second question: Is adding the gstreamer “queue” plugin the right component (Before PGIE) to be used here, to ensure frames are queued up with the correct ntp timestamp, or would it be better to have it in between PGIE and SGIE?