Digital planar surface segmentation using local geometric patterns

Yukiko Kenmochi (1) , Lilian Buzer (1) , Akihiro Sugimoto (2) , Ikuko Shimizu (3)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 NII - National Institute of Informatics
3 TUAT - Tokyo University of Agricuture and Technology

This paper presents a hybrid two-step method for segmenting a 3D grid-point cloud into planar surfaces by using discrete-geometry results. Digital planes contain a finite number of local geometric patterns (LGPs). Such a LGP possesses a set of normal vectors. By using LGP properties, we first reject non-linear points from a point cloud (edge-based step), and then classify non-rejected points whose LGPs have common normal vectors into a planar-surface-point set (region-based step).

Domaines: Informatique et langage [cs.CL]

Yukiko Kenmochi, Lilian Buzer, Akihiro Sugimoto, Ikuko Shimizu. Digital planar surface segmentation using local geometric patterns. Discrete Geometry for Computer Imagery, Apr 2008, Lyon, France. pp.322-333, ⟨10.1007/978-3-540-79126-3_29⟩. ⟨hal-00622082⟩