proj_match_points_distortion_ransacπ
Short descriptionπ
proj_match_points_distortion_ransac β Compute a projective transformation matrix between two images and
the radial distortion coefficient by automatically finding
correspondences between points.
Signatureπ
proj_match_points_distortion_ransac( image Image1, image Image2, point.y Rows1, point.x Cols1, point.y Rows2, point.x Cols2, string GrayMatchMethod, integer MaskSize, integer RowMove, integer ColMove, integer RowTolerance, integer ColTolerance, angle.rad Rotation, number MatchThreshold, string EstimationMethod, number DistanceThreshold, integer RandSeed, out hom_mat2d HomMat2D, out real Kappa, out real Error, out integer Points1, out integer Points2 )
Descriptionπ
Given a set of coordinates of characteristic points
\((\textrm{Rows1},\textrm{Cols1})\) and
\((\textrm{Rows2},\textrm{Cols2})\) in both input images
Image1 and Image2, which must be of identical
size, proj_match_points_distortion_ransac automatically
determines corresponding points, the homogeneous projective
transformation matrix HomMat2D, and the radial distortion
coefficient Kappa\(\kappa\)) that optimally fulfill the
following equation:
Here, \((r_{1},c_{1})\) and \((r_{2},c_{2})\) denote image points that are obtained by undistorting the input image points with the division model (see Calibration):
Here,
\((\tilde{r}_{1},\tilde{c}_{1}) = (\textrm{Rows1}-0.5(h-1), \textrm{Cols1}-0.5(w-1))\)
and
\((\tilde{r}_{2},\tilde{c}_{2}) = (\textrm{Rows2}-0.5(h-1), \textrm{Cols2}-0.5(w-1))\)
denote the distorted image points, specified relative to the image center,
and \(w\) and \(h\) denote the width and height of the input images.
Thus, proj_match_points_distortion_ransac assumes that the
principal point of the camera, i.e., the center of the radial
distortions, lies at the center of the image.
The returned Kappa can be used to construct camera
parameters that can be used to rectify images or points (see
change_radial_distortion_cam_par,
change_radial_distortion_image, and
change_radial_distortion_points):
The matching process is based on characteristic points, which can be
extracted with point operators like points_foerstner or
points_harris. The matching itself is carried out in two
steps: first, gray value correlations of mask windows around the
input points in the first and the second image are determined and an
initial matching between them is generated using the similarity of
the windows in both images. Then, the RANSAC algorithm is applied
to find the projective transformation matrix and radial distortion
coefficient that maximizes the number of correspondences under the
above constraint.
The size of the mask windows used for the matching is
MaskSize x
MaskSize. Three metrics for the correlation can be
selected. If GrayMatchMethod has the value 'ssd',
the sum of the squared gray value differences is used,
'sad' means the sum of absolute differences, and
'ncc' is the normalized cross correlation. For details
please refer to binocular_disparity. The metric is minimized
('ssd', 'sad') or maximized ('ncc') over
all possible point pairs. A thus found matching is only accepted if
the value of the metric is below the value of
MatchThreshold ('ssd', 'sad') or above
that value ('ncc').
To increase the algorithmβs performance, the search area for the match candidates can be limited to a rectangle by specifying its size and offset. Only points within a window of
points are considered. The offset of the
center of the search window in the second image with respect to the
position of the current point in the first image is given by
RowMove and ColMove.
If the transformation contains a rotation, i.e., if the first image
is rotated with respect to the second image, the parameter
Rotation may contain an estimate for the rotation angle or
an angle interval in radians. A good guess will increase the
quality of the gray value matching. If the actual rotation differs
too much from the specified estimate, the matching will typically
fail. In this case, an angle interval should be specified and
Rotation is a tuple with two elements. The larger the
given interval is the slower the operator is since the RANSAC
algorithm is run over all (automatically determined) angle
increments within the interval.
After the initial matching has been completed, a randomized search
algorithm (RANSAC) is used to determine the projective
transformation matrix HomMat2D and the radial distortion
coefficient Kappa. It tries to find the parameters that
are consistent with a maximum number of correspondences. For a
point to be accepted, the distance in pixels to its corresponding
transformed point must not exceed the threshold
DistanceThreshold.
The parameter EstimationMethod determines which algorithm
is used to compute the projective transformation matrix. A linear
algorithm is used if EstimationMethod is set to
'linear'. This algorithm is very fast and returns accurate
results for small to moderate noise of the point coordinates and for
most distortions (except for small distortions). For
EstimationMethod \(=\) 'gold_standard', a
mathematically optimal but slower optimization is used, which
minimizes the geometric reprojection error. In general, it is
preferable to use EstimationMethod \(=\)
'gold_standard'.
The value Error indicates the overall quality of the
estimation procedure and is the mean symmetric euclidean distance in
pixels between the points and their corresponding transformed
points.
Point pairs consistent with the above constraints are considered to
be corresponding points. Points1 contains the indices of
the matched input points from the first image and Points2
contains the indices of the corresponding points in the second
image.
The parameter RandSeed can be used to control the
randomized nature of the RANSAC algorithm, and hence to obtain
reproducible results. If RandSeed is set to a positive
number, the operator returns the same result on every call with the
same parameters because the internally used random number generator
is initialized with RandSeed. If RandSeed \(=\)
0, the random number generator is initialized with the
current time. In this case the results may not be reproducible.
The value set for the HALCON system variable 'seed_rand'
(see set_system) does not affect the results of
proj_match_points_distortion_ransac.
Execution informationπ
Execution information
-
Multithreading type: reentrant (runs in parallel with non-exclusive operators).
-
Multithreading scope: global (may be called from any thread).
-
Processed without parallelization.
Parametersπ
Image1 (input_object) singlechannelimage β object (byte / uint2)
Input image 1.
Image2 (input_object) singlechannelimage β object (byte / uint2)
Input image 2.
Rows1 (input_control) point.y-array β (real / integer)
Input points in image 1 (row coordinate).
Restriction: length(Rows1) >= 5
Cols1 (input_control) point.x-array β (real / integer)
Input points in image 1 (column coordinate).
Restriction: length(Cols1) == length(Rows1)
Rows2 (input_control) point.y-array β (real / integer)
Input points in image 2 (row coordinate).
Restriction: length(Rows2) >= 5
Cols2 (input_control) point.x-array β (real / integer)
Input points in image 2 (column coordinate).
Restriction: length(Cols2) == length(Rows2)
GrayMatchMethod (input_control) string β (string)
Gray value match metric.
Default: 'ncc'
List of values: 'ncc', 'sad', 'ssd'
MaskSize (input_control) integer β (integer)
Size of gray value masks.
Default: 10
Suggested values: 3, 7, 15
Value range: 1 β€ MaskSize
RowMove (input_control) integer β (integer)
Average row coordinate offset of corresponding points.
Default: 0
ColMove (input_control) integer β (integer)
Average column coordinate offset of corresponding points.
Default: 0
RowTolerance (input_control) integer β (integer)
Half height of matching search window.
Default: 200
Restriction: RowTolerance >= 1
ColTolerance (input_control) integer β (integer)
Half width of matching search window.
Default: 200
Restriction: ColTolerance >= 1
Rotation (input_control) angle.rad(-array) β (real / integer)
Estimate of the relative rotation of the second image with respect to the first image.
Default: 0.0
Suggested values: 0.0, 0.1, -0.1, 0.7854, 1.571, 3.142
MatchThreshold (input_control) number β (integer / real)
Threshold for gray value matching.
Default: 0.7
Suggested values: 0.9, 0.7, 0.5, 10, 20, 50, 100
EstimationMethod (input_control) string β (string)
Algorithm for the computation of the projective transformation matrix.
Default: 'gold_standard'
List of values: 'gold_standard', 'linear'
DistanceThreshold (input_control) number β (real / integer)
Threshold for the transformation consistency check.
Default: 1
Restriction: DistanceThreshold > 0
RandSeed (input_control) integer β (integer)
Seed for the random number generator.
Default: 0
HomMat2D (output_control) hom_mat2d β (real)
Computed homogeneous projective transformation matrix.
Kappa (output_control) real β (real)
Computed radial distortion coefficient.
Error (output_control) real β (real)
Root-Mean-Square transformation error.
Points1 (output_control) integer-array β (integer)
Indices of matched input points in image 1.
Points2 (output_control) integer-array β (integer)
Indices of matched input points in image 2.
Exampleπ
(HDevelop)
points_foerstner (Image1, 1, 2, 3, 50, 0.1, 'gauss', 'true', \
Rows1, Cols1, _, _, _, _, _, _, _, _)
points_foerstner (Image2, 1, 2, 3, 50, 0.1, 'gauss', 'true', \
Rows2, Cols2, _, _, _, _, _, _, _, _)
get_image_size (Image1, Width, Height)
proj_match_points_distortion_ransac (Image1, Image2, Rows1, Cols1, \
Rows2, Cols2, 'ncc', 10, 0, 0, \
Height, Width, 0, 0.5, \
'gold_standard', 1, 42, \
HomMat2D, Kappa, Error, \
Points1, Points2)
CamParDist := ['area_scan_division',0.0,Kappa,1.0,1.0, \
0.5*(Width-1),0.5*(Height-1),Width,Height]
change_radial_distortion_cam_par ('fixed', CamParDist, 0, CamPar)
change_radial_distortion_image (Image1, Image1, Image1Rect, \
CamParDist, CamPar)
change_radial_distortion_image (Image2, Image2, Image2Rect, \
CamParDist, CamPar)
concat_obj (Image1Rect, Image2Rect, ImagesRect)
gen_projective_mosaic (ImagesRect, MosaicImage, 1, 1, 2, HomMat2D, \
'default', 'false', MosaicMatrices2D)
Combinations with other operatorsπ
Combinations
Possible predecessors
points_foerstner, points_harris
Possible successors
vector_to_proj_hom_mat2d_distortion, change_radial_distortion_cam_par, change_radial_distortion_image, change_radial_distortion_points, gen_binocular_proj_rectification, projective_trans_image, projective_trans_image_size, projective_trans_region, projective_trans_contour_xld, projective_trans_point_2d, projective_trans_pixel
Alternatives
proj_match_points_distortion_ransac_guided
See also
proj_match_points_ransac, proj_match_points_ransac_guided, hom_vector_to_proj_hom_mat2d, vector_to_proj_hom_mat2d
Referencesπ
Richard Hartley, Andrew Zisserman: ``Multiple View Geometry in Computer Visionββ; Cambridge University Press, Cambridge; 2003.
Olivier Faugeras, Quang-Tuan Luong: ``The Geometry of Multiple Images: The Laws That Govern the Formation of Multiple Images of a Scene and Some of Their Applicationsββ; MIT Press, Cambridge, MA; 2001.
Moduleπ
Matching