I would like to use some of the OpenCV routines (2D convolve, Region Labeling, and Centroiding) in a CudaFy.net project.
- Is this a stupid idea?
- Would it be better just to implement the algorithms in C# from opensource examples?
- Some of inputs to the OpenCV have will already be in global GPU memory, can you pass pointers to OpenCV GPU routines and say the matrix is already in the GPU?
- Are there any simple examples of doing this
I did see one person who used EMGU and openCV but did run into some issues. Is there an example around of someone doing this successfully? [ https://cudafy.codeplex.com/discussions/356649 ]