Efficient RANSAC in Julia
Author cserteGT3
5 Stars
Updated Last
1 Year Ago
Started In
May 2019


Lifecycle Build Status Build status codecov.io

This package implements the efficient RANSAC algorithm for point clouds. Paper can be found here.

R. Schnabel, R. Wahl, R. Klein "Efficient RANSAC for Point-Cloud Shape Detection", in Computer Graphics Forum, Vol. 26, No. 2, pages 214-226, Blackwell Publishing, June 2007

Efficient RANSAC

The efficient RANSAC algorithm is used to segment and fit primitive shapes (sphere, plane, cylinder, torus, cone) to point clouds. Up to my knowledge, this is the first implementation in Julia.

Main features

  • easy-to-use primitive recognition
  • extensible: it's easy to add new primitive shapes
  • fast (work in progress)

Differences from the reference implementation

  • no bitmap
  • separate parameters for each shape
  • no tori

Getting started

Install the package by:

] add https://github.com/cserteGT3/RANSAC.jl

The input of the algorithm is a point cloud with associated surface normals. The output is a set of primitive shapes with corresponding sets of points, and the rest of the points that do not belong to any primitives.

Follow the detailed example in the documentation.

Here's an example with a point cloud and the detected primitives colored according to their type. RANSAC example