The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 689–695, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-689-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 689–695, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-689-2020

  12 Aug 2020

12 Aug 2020

HOLISTIC PARAMETRIC RECONSTRUCTION OF BUILDING MODELS FROM POINT CLOUDS

Z. Li1, W. Zhang2,1, and J. Shan1 Z. Li et al.
  • 1Lyles School of Civil Engineering, Purdue University, Indiana, USA
  • 2National Research Center of Cultural Industries, Central China Normal University, Wuhan, China

Keywords: Primitives, Building Modelling, Point Cloud, Semantic Segmentation, Deep Neural Network, CityGML

Abstract. Building models are conventionally reconstructed by building roof points via planar segmentation and then using a topology graph to group the planes together. Roof edges and vertices are then mathematically represented by intersecting segmented planes. Technically, such solution is based on sequential local fitting, i.e., the entire data of one building are not simultaneously participating in determining the building model. As a consequence, the solution is lack of topological integrity and geometric rigor. Fundamentally different from this traditional approach, we propose a holistic parametric reconstruction method which means taking into consideration the entire point clouds of one building simultaneously. In our work, building models are reconstructed from predefined parametric (roof) primitives. We first use a well-designed deep neural network to segment and identify primitives in the given building point clouds. A holistic optimization strategy is then introduced to simultaneously determine the parameters of a segmented primitive. In the last step, the optimal parameters are used to generate a watertight building model in CityGML format. The airborne LiDAR dataset RoofN3D with predefined roof types is used for our test. It is shown that PointNet++ applied to the entire dataset can achieve an accuracy of 83% for primitive classification. For a subset of 910 buildings in RoofN3D, the holistic approach is then used to determine the parameters of primitives and reconstruct the buildings. The achieved overall quality of reconstruction is 0.08 meters for point-surface-distance or 0.7 times RMSE of the input LiDAR points. This study demonstrates the efficiency and capability of the proposed approach and its potential to handle large scale urban point clouds.