A Framework for Automatic Modeling from Point Cloud Data

Author

Poullis, C.

Author_Institution

Immersive & Creative Technol. Lab., Cyprus Univ. of Technol., Limassol, Cyprus

Volume

35

Issue

11

fYear

2013

Firstpage

2563

Lastpage

2575

Abstract

We propose a complete framework for the automatic modeling from point cloud data. Initially, the point cloud data are preprocessed into manageable datasets, which are then separated into clusters using a novel two-step, unsupervised clustering algorithm. The boundaries extracted for each cluster are then simplified and refined using a fast energy minimization process. Finally, three-dimensional models are generated based on the roof outlines. The proposed framework has been extensively tested, and the results are reported.

Keywords

pattern clustering; solid modelling; 3D modeling; automatic modeling; fast energy minimization process; point cloud data; unsupervised clustering algorithm; Clustering algorithms; Covariance matrices; Data models; Solid modeling; Surface treatment; Three-dimensional displays; Vectors; 3D modeling; Three-dimensional reconstruction; clustering; point cloud; segmentation; shape refinement; Algorithms; Artificial Intelligence; Computer Simulation; Image Interpretation, Computer-Assisted; Models, Theoretical; Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2013.64

Filename

6487512