solvePnP with a priori known pitch and roll
How to correctly call solvePnP (for estimate the pose of a large ArUco board), if the board orientation (pitch and roll, not yaw) is known (from an IMU)?
Closest thing you can get is to call solvePnP with
SOLVEPNP_ITERATIVE
flag anduseExtrinsicGuess
set to true.But for this, you need to be close to the solution since PnP is a non-linear problem and to be able to converge to the actual solution. At least you would need to know approximatively the translation.
What if I have no information about translation, and about yaw rotation as well? Can this information help somehow to solvePnP?
Or I should just "replace" roll and pitch, keeping the yaw (it's not so trivial in fact) to make final result correct?