Volume IV-4/W4
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-4/W4, 101-108, 2017
https://doi.org/10.5194/isprs-annals-IV-4-W4-101-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-4/W4, 101-108, 2017
https://doi.org/10.5194/isprs-annals-IV-4-W4-101-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.

  13 Nov 2017

13 Nov 2017

SEMANTIC SEGMENTATION OF INDOOR POINT CLOUDS USING CONVOLUTIONAL NEURAL NETWORK

K. Babacan, L. Chen, and G. Sohn K. Babacan et al.
  • Dept. of Earth & Space Science & Engineering, York University, Toronto, M3J1P3, Canada

Keywords: Indoor Modelling, Semantic Segmentation, Mobile Laser, Point Cloud, Deep Learning, Convolutional Neural Network

Abstract. As Building Information Modelling (BIM) thrives, geometry becomes no longer sufficient; an ever increasing variety of semantic information is needed to express an indoor model adequately. On the other hand, for the existing buildings, automatically generating semantically enriched BIM from point cloud data is in its infancy. The previous research to enhance the semantic content rely on frameworks in which some specific rules and/or features that are hand coded by specialists. These methods immanently lack generalization and easily break in different circumstances. On this account, a generalized framework is urgently needed to automatically and accurately generate semantic information. Therefore we propose to employ deep learning techniques for the semantic segmentation of point clouds into meaningful parts. More specifically, we build a volumetric data representation in order to efficiently generate the high number of training samples needed to initiate a convolutional neural network architecture. The feedforward propagation is used in such a way to perform the classification in voxel level for achieving semantic segmentation. The method is tested both for a mobile laser scanner point cloud, and a larger scale synthetically generated data. We also demonstrate a case study, in which our method can be effectively used to leverage the extraction of planar surfaces in challenging cluttered indoor environments.