Package boofcv.alg.geo.pose


package boofcv.alg.geo.pose
  • Class
    Description
    Algorithms for finding a 4x4 homography which can convert two camera matrices of the same view but differ in only the projective ambiguity.
    Solves for the 3 unknown distances between camera center and 3 observed points by finding a root of a cubic polynomial and the roots of two quadratic polynomials.
    Solves for the 3 unknown distances between camera center and 3 observed points by finding the roots of a 4th order polynomial, This is probably the first solution to the P3P problem and first proposed in 1841 by Grunert.
    A related problem to the full P3P problem is to estimate the distance between the camera center and each of the 3 points being viewed.
    Computes the reprojection error squared for a given motion and Point2D3D.
    A plane based pose estimation algorithm [1].
    Computes the Jacobian of the error function in PnPResidualReprojection.
    Implementation of the EPnP algorithm from [1] for solving the PnP problem when N ≥ 5 for the general case and N ≥ 4 for planar data (see note below).
    Computes the predicted residual as a simple geometric distance between the observed and predicted point observation in normalized pixel coordinates.
    Encoding an decoding a rotation and translation where the rotation is encoded as a 3-vector Rodrigues coordinate.
    Computes sum of reprojection error squared in pixels for a pair of stereo observations.
    Computes the left camera pose from a fully calibrated stereo camera system using a PnP algorithm.
    Computes the Jacobian of the error function in PnPResidualReprojection.
    Minimizes the reprojection residual error for a pose estimate (left camera) in a calibrated stereo camera.
    Computes the predicted residual as a simple geometric distance between the observed and predicted point observation in normalized pixel coordinates.
    Provides the distance each point is from the camera center.
    Estimates the camera motion using linear algebra given a set of N associated point observations and the depth (z-coordinate) of each object, where N ≥ 6.
    Given two views of N objects and the known rotation, estimate the translation.
    Estimates a projective camera given N points, i.e.
    Refines a pose estimate given a set of stereo observations and associated 3D point in world coordinates.
    Used in case 4 of EPnP.
    Allows a ModelCodec for Se3_F64 to be used by StereoPose.
    Various utility functions for PnPLepetitEPnP.