Graph Cut Based Point-Cloud Segmentation for Polygonal Reconstruction

The reconstruction of 3D objects from a point-cloud is based on sufficient separation of the points representing objects of interest from the points of other, unwanted objects. This operation called segmentation is discussed in this paper. We present an interactive unstructured pointcloud segmentation based on graph cut method where the cost function is derived from euclidean distance of point-cloud points. The graph topology and direct 3D point-cloud segmentation are the novel parts of our work. The segmentation is presented on real application, the terrain reconstruction of a complex miniature paper model, the Langweil model of Prague.

• Type: Conference
• Year: 2009
• Where: ISVC
• Authors: David Sedlacek, Jiri Zara
• Keywords: ISVC 2009, Operation Called Segmentation, Point-cloud Segmentation, Unstructured Pointcloud Segmentation