Skip to content

Point

Point

class Point():
 |  Point()

Implementation for Point RANSAC.

This object finds the coordinate of a point in 3D space using RANSAC method. The point with more neighbors in a determined radius (thresh) will be selected as the best candidate.

3D point

fit

 | fit(pts, thresh=0.2, maxIteration=10000)

Find the best point for the 3D Point representaiton. The Point in a 3d enviroment is defined as a X, Y Z coordinate with more neighbors around.

Arguments:

  • pts: 3D point cloud as a np.array (N,3).
  • thresh: Threshold radius from the point which is considered inlier.
  • maxIteration: Number of maximum iteration which RANSAC will loop over.

Returns:

  • center: Point selected as best candidate np.array (1, 3)
  • inliers: Inlier's index from the original point cloud. np.array (1, M)