Redundent frames handling of DeepStream

Hi there.
I was using DeepStream for inferring a live video input from a usb-cam. The frame rate of the camera was set to 30 fps and the frame processing speed was 10 fps according to DeepStream performance measurement. So were the excessive frames provided by the camera dropped? I’m trying understand how DeepStream handle such speed misalignment.

My setup is the following:

Jetson Xavier
DeepStream 5.0
JetPack 4.4
TensorRT 7.1.3
NVIDIA GPU Driver Version 10.2

Camera can drop video frame if video buffer don’t return on time.

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