Background subtractor on Jetson Nano

I use VPI background subtraction (vpi.BackgroundSubtractor) on the jetson nano. The results were not what I expected. With openCV MOG CPU on the jetson nano, the processing of about (1503 1920x1080 frames) took about 10 Frames Per Second . VPI CUDA subtraction took 5 Frames Per Second on the jetson nano, VPI CPU subtraction took 1 Frames Per Second. Is CV2 MOG background subtraction a much faster process than what VPI background subtraction uses? Am I not using VPI background subtraction correctly? The faster the better! Any pointers would help. Is there any benchmark data for the background subtractor on Jetson Nano?

Hi,

You can the performance below:
https://docs.nvidia.com/vpi/1.2/algo_background_subtractor.html#algo_background_subtractor_perf

[1920x1080/u8] CPU: 55.8±0.5 ms GPU: 39.7±0.6 ms

Thanks.

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