I am new in Computer Vision. Suppose you have 8 points (players in a basketball court) in a 2D image (png photo), that is we know the pixel coordinates of each. I would like to compute camera position w.r.t. the field. We have the actual dimensions of the field. Also, I can write the equations of two or three transversal lines in the field that are parallels lines from top view. With this data can we find a position vector of the camera w.r.t. the field ?

Any idea on where to read about this ?


You said you could see lines, so I assume you could see their intersections. If you could assume to have at least 4 fixed points of the court which are always visible (corners might be a good choice), this problem is similar to the 3D pose estimation problem, since you are essentially looking for a pose (position and orientation) of a known 3D object in a 2D image.

You might find it useful to read about POSIT, an iterative algorithm published in 1992 and there is also this algorithm from 1999. Both algorithm solve the 3D pose estimation problem.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.