How to define an image processing algorithm in VPI? What is noteworthy? We just need to be able to run on CUDA and CPU.
If the function is in OpenCV, you may manually build/install OpenCV with CUDA filters. A user has shared a script and please give it a try:
GitHub - mdegans/nano_build_opencv: Build OpenCV on Nvidia Jetson Nano
What I want to express is how to build opencv algorithm in VPI that has not been ported? For example, I want to implement Karman filter in VPI. How do I build this algorithm?
Hey, I asked about a user defined function here, but I didn’t get to testing it yet: