ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume X-4/W2-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., X-4/W2-2022, 305–310, 2022
https://doi.org/10.5194/isprs-annals-X-4-W2-2022-305-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., X-4/W2-2022, 305–310, 2022
https://doi.org/10.5194/isprs-annals-X-4-W2-2022-305-2022
 
14 Oct 2022
14 Oct 2022

SEMANTIC SEGMENTATION OF INDOOR 3D POINT CLOUDS BY JOINT OPTIMIZATION OF GEOMETRIC FEATURES AND NEURAL NETWORKS

M. M. Yao1,2, X. M. Li1,2, W. X. Wang1,2, L. F. Xie1,2, and S. J. Tang1,2 M. M. Yao et al.
  • 1School of Architecture and Urban Planning, Research Institute for Smart Cities, Shenzhen University, China
  • 2Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, China

Keywords: Neural Network, Point Clouds, Plane Extraction, Region-growing Segmentation

Abstract. Indoor navigation, indoor robotics, and other deep applications of interior space can be realized through semantic segmentation of 3D point clouds. We propose a semantic segmentation method for point clouds that uses geometric features of point clouds and neural networks to address the problem of incomplete and inconsistent segmentation objectives in existing semantic segmentation methods. Using neural networks, semantic labels are extracted from indoor structural information as the first step. The paper proposes a probabilistic model to cross-validate the initial segmentation results with the segmentation results of geometric features to achieve joint optimization of the results for semantic segmentation. Three sets of indoor point clouds data from simple to complex indoor scenes are used to test the accuracy and validity of the segmentation method proposed in this paper. The experimental results demonstrate that the method proposed in this paper can effectively improve the semantic segmentation accuracy of indoor 3D point clouds.