The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B5-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B5-2022, 73–78, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B5-2022-73-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B5-2022, 73–78, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B5-2022-73-2022
 
02 Jun 2022
02 Jun 2022

FROM BIM TO POINTCLOUD: AUTOMATIC GENERATION OF LABELED INDOOR POINTCLOUD

H. S. Huang1,2, S. J. Tang1,2, W. X. Wang1,2, X. M. Li1,2, and R. Z. Guo1,2 H. S. Huang et al.
  • 1School of Architecture and Urban Planning, Research Institute for Smart Cities, Shenzhen University, P.R. China
  • 2Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen, P.R. China

Keywords: Building information model, Deep learning, Semantic segmentation, Synthetic dataset, Point clouds

Abstract. With the development of deep learning technology, a large number of indoor spatial applications, such as robotics and indoor navigation, have raised higher data requirements for indoor semantic model. However, creating deep learning classifiers requires a large number of labeled datasets, and the collection of such datasets requires a lot of manually labeling proces, which is labor-intensive and time-consuming. In this paper, we propose a method to automatically create 3D point clouds datasets with indoor semantic labels based on parametric BIM model. First, a automatic BIM generation method is proposed through simulating the structure of interior space Secondly, we use a viewpoint-guided labeled point cloud generation method to generate synthetic 3D point clouds with different labels, color information. Especially, noise are also simulated with a gaussian model. As shown in the experiments, the point cloud data with labels can be quickly obtained from existing BIM models, which will largely reduce the complexity of data labeling and improve efficiency. These simulated data can be used in the deep learning training process and improve the semantic segmentation accuracy.