From 660d7cd3aeb06c4eba5d498ab3b2ec069ae5326c Mon Sep 17 00:00:00 2001 From: Daniel Angelov Date: Mon, 16 Jun 2014 13:05:17 +0100 Subject: [PATCH] Updated findHomography docs branch 2.4 Updated the documents to give warning to the users of `findHomography` that the function may return an empty matrix in some cases. The user must take care of checking that. --- modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst b/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst index 8afc5ce..d616dfd 100644 --- a/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst +++ b/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst @@ -746,7 +746,7 @@ is minimized. If the parameter ``method`` is set to the default value 0, the fun uses all the point pairs to compute an initial homography estimate with a simple least-squares scheme. However, if not all of the point pairs ( -:math:`srcPoints_i`,:math:`dstPoints_i` ) fit the rigid perspective transformation (that is, there +:math:`srcPoints_i`, :math:`dstPoints_i` ) fit the rigid perspective transformation (that is, there are some outliers), this initial estimate will be poor. In this case, you can use one of the two robust methods. Both methods, ``RANSAC`` and ``LMeDS`` , try many different random subsets of the corresponding point pairs (of four pairs each), estimate @@ -769,7 +769,7 @@ if there are no outliers and the noise is rather small, use the default method ( The function is used to find initial intrinsic and extrinsic matrices. Homography matrix is determined up to a scale. Thus, it is normalized so that -:math:`h_{33}=1` . +:math:`h_{33}=1`. Note that whenever an H matrix cannot be estimated, an empty one will be returned. .. seealso:: -- 2.7.4