Computes an optimal affine transformation between two 3D point sets

M = cv.estimateAffine3D(src, dst)
[M, inliers] = cv.estimateAffine3D(...)
[...] = cv.estimateAffine3D(..., 'OptionName', optionValue, ...)

Input

• src First input 3D point set containing (X,Y,Z). Cell array of 3-element vectors {[x,y,z],...} or Nx3/Nx1x3/1xNx3 numeric array.
• dst Second input 3D point set containing (x,y,z). Same size and type as src.

Output

• M Output 3D affine transformation matrix 3x4 of the form [a11 a12 a13 b1; a21 a22 a23 b2; a31 a32 a33 b3]
• inliers Output vector of same length as number of points, indicating which points are inliers (1-inlier, 0-outlier).
• result success flag.

Options

• RansacThreshold Maximum reprojection error in the RANSAC algorithm to consider a point as an inlier. default 3.0.
• Confidence Confidence level, between 0 and 1, for the estimated transformation. Anything between 0.95 and 0.99 is usually good enough. Values too close to 1 can slow down the estimation significantly. Values lower than 0.8-0.9 can result in an incorrectly estimated transformation. default 0.99.

It computes:

[x; y; z] = [a11 a12 a13; a21 a22 a23; a31 a32 a33] * [X; Y; Z] + [b1; b2; b3]

The function estimates an optimal 3D affine transformation between two 3D point sets using the RANSAC algorithm.