Abstract
Abstract. Automatic 3D building reconstruction from laser scanning or photogrammetric point clouds has gained increasing attention in the past two decades. Although many efforts have been made, the complexity of buildings and incompletion of point clouds, i.e., data missing, still make it a challenging task for automatic 3D reconstruction of buildings in large-scale urban scenes with various architectural styles. This paper presents an innovative approach for automatic generation of 3D models of complex buildings from even incomplete point clouds. The approach first decomposes the 3D space into multiple space units, including 3D polyhedral cells, facets and edges, where the facets and edges are also encoded with topological-relation constraints. Then, the units and constraints are used together to approximate the buildings. On one hand, by extracting facets from 3D cells and further extracting edges from facets, this approach simplifies complicated topological computations. On the other hand, because this approach models buildings on the basis of polyhedral cells, it can guarantee that the models are manifold and watertight and avoid correcting topological errors. A challenging dataset containing 105 buildings acquired in Central, Hong Kong, was used to evaluate the performance of the proposed approach. The results were compared with two previous methods and the comparisons suggested that the proposed approach outperforms other methods in terms of robustness, regularity, and accuracy of the models, with an average root-mean-square error of less than 0.9 m. The proposed approach is of significance for automatic 3D modelling of buildings for urban applications.
Highlights
Three-dimensional (3D) reconstruction from point clouds has been an active topic in photogrammetry and computer vision communities
The complexity of buildings increases the difficulties in topological computation in model-driven and hybrid-driven methods (Vosselman and Dijkman, 2001; Sohn et al, 2008; Verma et al, 2006), resulting in crack effects in the final models (Poullis, 2013; Xie et al, 2018) or needing extra work to correct the topological errors in the models manually (Xiong et al, 2014)
We propose an innovative and robust approach for automatic generation of 3D building models, regardless the complexity of buildings and the incompletion of point clouds
Summary
Three-dimensional (3D) reconstruction from point clouds has been an active topic in photogrammetry and computer vision communities. A recent trend of generating building models is to decompose the 3D space into a set of basic units, e.g., boxes, facets and cells, and use these basic units to fit the building surfaces (Li et al, 2016; Nan and Wonka, 2017; Verdie et al, 2015) This strategy avoids error-prone topological computations during the reconstruction and is able to produce true 3D building models. An innovative approach for 3D reconstruction of complex buildings from even incomplete point clouds is developed This method adopts a space-decomposition-andapproximation strategy; but unlike previous methods, the topological relations between the basic space units are extracted after space decomposition. Experiments with point clouds containing 105 buildings in Central, Hong Kong, were carried out to evaluate the performance of the proposed approach
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
