Hello, is it possible to accelerate camera reading for opencv and reduce cpu load (maybe use cuda?) ? Now I am using something like this for camera init in opencv: camSet=‘nvarguscamerasrc ! video/x-raw(memory:NVMM), width=1280, height=720, format=NV12, framerate=60/1 ! nvvidconv flip-method=‘2’ ! video/x-raw, width=‘1280’, height=‘720’, format=BGRx ! videoconvert ! video/x-raw, format=BGR ! appsink’
Thank you
hello w1ngedshadow,
may I know what’s the actual use-case, and please also share the expectations.
thanks
I am bulding robot with two cameras for competitions based on jetson nano. When I run my programm CPU is fully loaded but GPU is not. So I want to maximize the use of GPU.
hello w1ngedshadow,
what’s your sensor types? OpenCV it needs RGB formats, so there’s format conversion that consume some resources.
btw, you may see-also the sample application for camera capture CUDA processing, 12_camera_v4l2_cuda.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.