Min-Cut Based Segmentation of Point Clouds

Free registration required

Executive Summary

The authors present a min-cut based method of segmenting objects in point clouds. Given an object location, the method builds a k-nearest neighbors graph, assumes a background prior, adds hard foreground (and optionally background) constraints, and finds the min-cut to compute a foreground background segmentation. The method can be run fully automatically, or interactively with a user interface. They test the system on an outdoor urban scan, quantitatively evaluate the algorithm on a test set of about 1000 objects, and compare to several alternative approaches.

  • Format: PDF
  • Size: 1761.7 KB