Construct a bundle adjuster instance

obj = cv.BundleAdjuster(adjusterType)
obj = cv.BundleAdjuster(adjusterType, 'OptionName',optionValue, ...)

Input

• adjusterType Bundle adjustment cost function. One of:
  • NoBundleAdjuster Stub bundle adjuster that does nothing.
  • BundleAdjusterRay Implementation of the camera parameters refinement algorithm which minimizes sum of the distances between the rays passing through the camera center and a feature. It can estimate focal length. It ignores the refinement mask for now.
  • BundleAdjusterReproj Implementation of the camera parameters refinement algorithm which minimizes sum of the reprojection error squares. It can estimate focal length, aspect ratio, principal point. You can affect only on them via the refinement mask.
  • BundleAdjusterAffine Bundle adjuster that expects affine transformation represented in homogeneous coordinates in R for each camera param. Implements camera parameters refinement algorithm which minimizes sum of the reprojection error squares. It estimates all transformation parameters. Refinement mask is ignored. See also cv.AffineBasedEstimator and AffineBestOf2NearestMatcher.
  • BundleAdjusterAffinePartial Bundle adjuster that expects affine transformation with 4 DOF represented in homogeneous coordinates in R for each camera param. Implements camera parameters refinement algorithm which minimizes sum of the the reprojection error squares. It estimates all transformation parameters. Refinement mask is ignored.

Options

The following are options accepted by all adjusters:

• ConfThresh Threshold to filter out poorly matched image pairs. default 1
• RefinementMask 3x3 8-bit mask, where 0 means don't refine respective parameter, non-zero means refine. default eye(3,'uint8')
• TermCriteria Levenberg-Marquardt algorithm termination criteria. default struct('type','Count+EPS', 'maxCount',1000, 'epsilon',eps)