Image processing using OpenCV on OpenGL graphics

As title says, I want to know if there is a way to process graphics using OpenCV created by OpenGL?
I am displaying thousands of points in real-time using OpenGL. Now I want to create clusters for those points and later point-tracking.
I have found this but couldn't understand it well.
Apart from that on this page a guy mentioned "OpenCV generally operates on real image data, and wouldn't operate on graphics generated by OpenGL."
Is it true?