This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
You don't. You would use solvePnP to get the location of a camera relative to a set of points already known by some other method. For example, if your camera moved, then in the next frame, you would find the same points again, and use solvePnP to locate the camera's new position and orientation.
Or if you have a known set of points, you could use it to get the location of the camera without needing a second camera.
