Hi. It seems OpenVX’s goal is to speed up the image processing algorithms. However OpenCV provides CUDA and OpenCL implementation to make the processing much faster on x86/amd64 based systems. Even on mobile devices OpenCL is also supported, meaning we speed up image processing on mobile devices by OpenCL.
So why do we need OpenVX? Thanks.
OpenVX’s goal is to accelerate all vision functions, not just image processing. OpenCV has some acceleration mechanisms now, but not all that are possible. OpenVX allows those new possibilities and more since it’s graph based. OpenCV will use OpenVX as the acceleration layer in the future. If you vision problems are amenable to being expressed as graphs with the nodes that OpenVX will support then use OpenVX over OpenCV, if not you should still get some lift with OpenCV’s use of OpenVX.