1

According that post Detecting set of planes from point cloud I'm doing the same, but I don't know how to proceed with the algorithm in python. Would someone point a pseudo code for the algorithm in python ? Or using any helper library like scipy ?

I'm trying to detect two planes (two walls with an edge) and I need their normals

The algorithm that is mentioned:

Pick 3 points at random.
Make a plane.
Check if each other point lies on the plane.
If enough are on the plane - recalculate a best plane from all these points and remove them from the set
If not try another 3 points
Stop when you have enough planes, or too few points left.
andre
  • 53
  • 6
  • clustering? https://towardsdatascience.com/the-5-clustering-algorithms-data-scientists-need-to-know-a36d136ef68 – G. B. Feb 22 '19 at 10:15
  • @G.B. Good idea, so I cluster the points into 2 clusers, then fit the plane for each cluster? can you write an answer with detailed approach ? – andre Feb 22 '19 at 10:47
  • you need to first parameterize (in finite space) and then do a sweep, followed by some sort of clustering technique. For example [hough transformation](https://www.researchgate.net/publication/228754371_The_3D_Hough_Transform_for_plane_detection_in_point_clouds_A_review_and_a_new_accumulator_design). – Prodipta Ghosh Feb 22 '19 at 11:15
  • What do you mean if someone has a **pseudo code**? You literally posted a pseudo code for your problem, why don't you try and implement it? BTW, the algorithm you are looking for is called [RANSAC](https://en.wikipedia.org/wiki/Random_sample_consensus). – serkan.tuerker Feb 22 '19 at 22:16

0 Answers0