match_rel_pose_ransacT_match_rel_pose_ransacMatchRelPoseRansacMatchRelPoseRansac (Operator)

Name

match_rel_pose_ransacT_match_rel_pose_ransacMatchRelPoseRansacMatchRelPoseRansac — Compute the relative orientation between two cameras by automatically finding correspondences between image points.

Signature

Description

Given a set of coordinates of characteristic points (Rows1Rows1Rows1Rows1rows1,Cols1Cols1Cols1Cols1cols1) and (Rows2Rows2Rows2Rows2rows2,Cols2Cols2Cols2Cols2cols2) in the stereo images Image1Image1Image1Image1image1 and Image2Image2Image2Image2image2 along with known internal camera parameters CamPar1CamPar1CamPar1CamPar1camPar1 and CamPar2CamPar2CamPar2CamPar2camPar2, match_rel_pose_ransacmatch_rel_pose_ransacMatchRelPoseRansacMatchRelPoseRansacMatchRelPoseRansac automatically determines the geometry of the stereo setup and finds the correspondences between the characteristic points. The geometry of the stereo setup is represented by the relative pose RelPoseRelPoseRelPoseRelPoserelPose and all corresponding points have to fulfill the epipolar constraint. RelPoseRelPoseRelPoseRelPoserelPose indicates the relative pose of camera 1 with respect to camera 2 (See create_posecreate_poseCreatePoseCreatePoseCreatePose for more information about poses and their representations.). This is in accordance with the explicit calibration of a stereo setup using the operator calibrate_camerascalibrate_camerasCalibrateCamerasCalibrateCamerasCalibrateCameras. Now, let R,t be the rotation and translation of the relative pose. Then, the essential matrix E is defined as , where denotes the 3x3 skew-symmetric matrix realising the cross product with the vector t. The pose can be determined from the epipolar constraint:

Note, that the essential matrix is a projective entity and thus is defined up to a scaling factor. From this follows that the translation vector of the relative pose can only be determined up to scale too. In fact, the computed translation vector will always be normalized to unit length. As a consequence, a subsequent threedimensional reconstruction of the scene, using for instance vector_to_rel_posevector_to_rel_poseVectorToRelPoseVectorToRelPoseVectorToRelPose, can be carried out only up to a single global scaling factor.

The operator match_rel_pose_ransacmatch_rel_pose_ransacMatchRelPoseRansacMatchRelPoseRansacMatchRelPoseRansac is designed to deal with a camera model, that includes lens distortions. This is in contrast to the operator match_essential_matrix_ransacmatch_essential_matrix_ransacMatchEssentialMatrixRansacMatchEssentialMatrixRansacMatchEssentialMatrixRansac, which encompasses only straight line preserving cameras. The camera parameters are passed in CamPar1CamPar1CamPar1CamPar1camPar1 and CamPar2CamPar2CamPar2CamPar2camPar2. The 3D direction vectors and are calculated from the point coordinates (Rows1Rows1Rows1Rows1rows1,Cols1Cols1Cols1Cols1cols1) and (Rows2Rows2Rows2Rows2rows2,Cols2Cols2Cols2Cols2cols2) by inverting the process of projection (see calibrate_camerascalibrate_camerasCalibrateCamerasCalibrateCamerasCalibrateCameras).

The matching process is based on characteristic points, which can be extracted with point operators like points_foerstnerpoints_foerstnerPointsFoerstnerPointsFoerstnerPointsFoerstner or points_harrispoints_harrisPointsHarrisPointsHarrisPointsHarris. 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 relative pose that maximizes the number of correspondences under the epipolar constraint.

The size of the mask windows is MaskSizeMaskSizeMaskSizeMaskSizemaskSize x MaskSizeMaskSizeMaskSizeMaskSizemaskSize. Three metrics for the correlation can be selected. If GrayMatchMethodGrayMatchMethodGrayMatchMethodGrayMatchMethodgrayMatchMethod has the value 'ssd'"ssd""ssd""ssd""ssd", the sum of the squared gray value differences is used, 'sad'"sad""sad""sad""sad" means the sum of absolute differences, and 'ncc'"ncc""ncc""ncc""ncc" is the normalized cross correlation. For details please refer to binocular_disparitybinocular_disparityBinocularDisparityBinocularDisparityBinocularDisparity. The metric is minimized ('ssd'"ssd""ssd""ssd""ssd", 'sad'"sad""sad""sad""sad") or maximized ('ncc'"ncc""ncc""ncc""ncc") over all possible point pairs. A thus found matching is only accepted if the value of the metric is below the value of MatchThresholdMatchThresholdMatchThresholdMatchThresholdmatchThreshold ('ssd'"ssd""ssd""ssd""ssd", 'sad'"sad""sad""sad""sad") or above that value ('ncc'"ncc""ncc""ncc""ncc").

To increase the speed of the algorithm, the search area for the matchings can be limited. 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 RowMoveRowMoveRowMoveRowMoverowMove and ColMoveColMoveColMoveColMovecolMove.

If the second camera is rotated around the optical axis with respect to the first camera the parameter RotationRotationRotationRotationrotation 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 RotationRotationRotationRotationrotation is a tuple with two elements. The larger the given interval the slower the operator is since the RANSAC algorithm is run over all angle increments within the interval.

After the initial matching is completed a randomized search algorithm (RANSAC) is used to determine the relative pose RelPoseRelPoseRelPoseRelPoserelPose. It tries to find the relative pose that is consistent with a maximum number of correspondences. For a point to be accepted, the distance to its corresponding epipolar line must not exceed the threshold DistanceThresholdDistanceThresholdDistanceThresholdDistanceThresholddistanceThreshold.

The parameter EstimationMethodEstimationMethodEstimationMethodEstimationMethodestimationMethod decides whether the relative orientation between the cameras is of a special type and which algorithm is to be applied for its computation. If EstimationMethodEstimationMethodEstimationMethodEstimationMethodestimationMethod is either 'normalized_dlt'"normalized_dlt""normalized_dlt""normalized_dlt""normalized_dlt" or 'gold_standard'"gold_standard""gold_standard""gold_standard""gold_standard" the relative orientation is arbitrary. Choosing 'trans_normalized_dlt'"trans_normalized_dlt""trans_normalized_dlt""trans_normalized_dlt""trans_normalized_dlt" or 'trans_gold_standard'"trans_gold_standard""trans_gold_standard""trans_gold_standard""trans_gold_standard" means that the relative motion between the cameras is a pure translation. The typical application for this special motion case is the scenario of a single fixed camera looking onto a moving conveyor belt. In order to get a unique solution in the correspondence problem the minimum required number of corresponding points is six in the general case and three in the special, translational case.

The relative pose is computed by a linear algorithm if 'normalized_dlt'"normalized_dlt""normalized_dlt""normalized_dlt""normalized_dlt" or 'trans_normalized_dlt'"trans_normalized_dlt""trans_normalized_dlt""trans_normalized_dlt""trans_normalized_dlt" is chosen. With 'gold_standard'"gold_standard""gold_standard""gold_standard""gold_standard" or 'trans_gold_standard'"trans_gold_standard""trans_gold_standard""trans_gold_standard""trans_gold_standard" the algorithm gives a statistically optimal result, and returns as well the covariance of the relative pose CovRelPoseCovRelPoseCovRelPoseCovRelPosecovRelPose. Here, 'normalized_dlt' and 'gold_standard' stand for direct-linear-transformation and gold-standard-algorithm respectively. Note, that in general the found correspondences differ depending on the deployed estimation method.

The value ErrorErrorErrorErrorerror indicates the overall quality of the estimation procedure and is the mean euclidian distance in pixels between the points and their corresponding epipolar lines.

Point pairs consistent with the mentioned constraints are considered to be in correspondences. Points1Points1Points1Points1points1 contains the indices of the matched input points from the first image and Points2Points2Points2Points2points2 contains the indices of the corresponding points in the second image.

For the operator match_rel_pose_ransacmatch_rel_pose_ransacMatchRelPoseRansacMatchRelPoseRansacMatchRelPoseRansac a special configuration of scene points and cameras exists: if all 3D points lie in a single plane and additionally are all closer to one of the two cameras then the solution in the essential matrix is not unique but twofold. As a consequence both solutions are computed and returned by the operator. This means that the output parameters RelPoseRelPoseRelPoseRelPoserelPose, CovRelPoseCovRelPoseCovRelPoseCovRelPosecovRelPose and ErrorErrorErrorErrorerror are of double length and the values of the second solution are simply concatenated behind the values of the first one.

The parameter RandSeedRandSeedRandSeedRandSeedrandSeed can be used to control the randomized nature of the RANSAC algorithm, and hence to obtain reproducible results. If RandSeedRandSeedRandSeedRandSeedrandSeed is set to a positive number the operator yields the same result on every call with the same parameters because the internally used random number generator is initialized with the RandSeedRandSeedRandSeedRandSeedrandSeed. If RandSeedRandSeedRandSeedRandSeedrandSeed = 0 the random number generator is initialized with the current time. In this case the results may not be reproducible.

Execution Information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).
• Multithreading scope: global (may be called from any thread).
• Processed without parallelization.

Parameters

Possible Predecessors

points_foerstnerpoints_foerstnerPointsFoerstnerPointsFoerstnerPointsFoerstner, points_harrispoints_harrisPointsHarrisPointsHarrisPointsHarris

Possible Successors

vector_to_rel_posevector_to_rel_poseVectorToRelPoseVectorToRelPoseVectorToRelPose, gen_binocular_rectification_mapgen_binocular_rectification_mapGenBinocularRectificationMapGenBinocularRectificationMapGenBinocularRectificationMap

See also

binocular_calibrationbinocular_calibrationBinocularCalibrationBinocularCalibrationBinocularCalibration, match_fundamental_matrix_ransacmatch_fundamental_matrix_ransacMatchFundamentalMatrixRansacMatchFundamentalMatrixRansacMatchFundamentalMatrixRansac, match_essential_matrix_ransacmatch_essential_matrix_ransacMatchEssentialMatrixRansacMatchEssentialMatrixRansacMatchEssentialMatrixRansac, create_posecreate_poseCreatePoseCreatePoseCreatePose

References

Richard Hartley, Andrew Zisserman: “Multiple View Geometry in Computer Vision”; 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 Applications”; MIT Press, Cambridge, MA; 2001.

Module

3D Metrology