Package boofcv.alg.geo.selfcalib
package boofcv.alg.geo.selfcalib
-
ClassesClassDescriptionImage based reprojection error using error in view 2 and view 3.If the camera calibration is known for two views then given canonical camera projection matrices (P1 = [I|0]) it is possible to compute the plane a infinity and from that elevate the views from projective to metric.Results of upgrading a three view scenario from a projective into a metric scene.Non-linear refinement of Dual Quadratic using algebraic error.Non-linear refinement of intrinsics and rotation while under pure rotation given two views and associated features.There's a sign ambiguity which flips the translation vector for several self calibration functions.view[0] is assumed to the located at coordinate system's origin.Brute force sampling approach to perform self calibration of a partially calibrated image.Computes intrinsic calibration matrix for each view using projective camera matrices to compute the the dual absolute quadratic (DAQ) and by assuming different elements in the 3x3 calibration matrix have linear constraints.Camera calibration for when the camera's motion is purely rotational and has no translational component and camera parameters can change every frame.Camera calibration for when the camera's motion is purely rotational and has no translational component and camera parameters are assumed to be constant.Computes the best projective to metric 4x4 rectifying homography matrix by guessing different values for focal lengths of the first two views.Estimates the calibrating/rectifying homography when given a trifocal tensor and two calibration matrices for the first two views.