Hi everyone, I want to obtain the 3D coordinate from my video stream of a person's head. I've got X,Y coordinates for the head centroid and what I need now is the Z coordinate. I also have the depth of the person from the camera.
However, when I came across with this function:
I couldn't quite understand the parameters used. What does float point represent and also "intrinsic"? and why is the point in array type? Thank you
could anyone explain to me of all these parameters? I only know the basic of them.
Thanks for posting in the RealSense community.
The information you are looking for is explained in the following Github link: