CentralCamera.estpose#

CentralCamera.estpose(P: ndarray, p: ndarray, method: str = 'iterative', frame: str = 'world') SE3 | None[source]#

Estimate object pose

Parameters:
  • P (ndarray(3, N)) – A set of 3D points defining the object with respect to its own frame

  • p (ndarray(2, N)) – Image plane projection of the object points

  • method (str, optional) – pose estimation algorithm, see OpenCV solvePnP, defaults to ‘iterative’

  • frame (str, optional) – estimate pose with respect to frame “world” [default] or “camera”

Returns:

pose of target frame relative to the world frame

Return type:

SE3

Using a set of points defining some object with respect to its own frame {B}, and a set of image-plane projections, estimate the pose of {B} with respect to the world or camera frame.

To estimate the camera’s pose with respect to the world frame the camera’s pose self.pose is used.

Note

  • All of the OpenCV estimation algorithms are supported.

  • Algorithm "ippe-square" requires exactly four points at the corners of a square and in the order: (-x, y), (x, y), (x, -y), (-x, -y).

Seealso:

project_point opencv.solvePnP