Layout graph model for semantic façade reconstruction using laser point clouds

Abstract

Building façades can feature different patterns depending on the architectural style, functionality, and size of the buildings; therefore, reconstructing these façades can be complicated. In particular, when semantic façades are reconstructed from point cloud data, uneven point density and noise make it difficult to accurately determine the façade structure. When investigating façade layouts, Gestalt principles can be applied to cluster visually similar floors and façade elements, allowing for a more intuitive interpretation of façade structures. We propose a novel model for describing façade structures, namely the layout graph model, which involves a compound graph with two structure levels. In the proposed model, similar façade elements such as windows are first grouped into clusters. A down-layout graph is then formed using this cluster as a node and by combining intra-and inter-cluster spacings as the edges. Second, a top-layout graph is formed by clustering similar floors. By extracting relevant parameters from this model, we transform semantic façade reconstruction to an optimization strategy using simulated annealing coupled with Gibbs sampling. Multiple façade point cloud data with different features were selected from three datasets to verify the effectiveness of this method. The experimental results show that the proposed method achieves an average accuracy of 86.35%. Owing to its flexibility, the proposed layout graph model can deal with different types of façades and qualities of point cloud data, enabling a more robust and accurate reconstruction of façade models.

Tum-Façade: Reviewing and Enriching Point Cloud Benchmarks for Façade Segmentation

“…Of the particular interest are point clouds acquired by MLS vehicles thanks to their, high temporal resolution, and the density of the street-level point clouds (Wysocki et al, 2021a). This has led to a recent growth in interest in developing methods of parsing fac ¸ades using point clouds (Martinovic et al, 2015, Fan et al, 2021, Zolanvari and Laefer, 2016, especially using machine learning methods (Matrone et al, 2020, Liu et al, 2020.…”

Detailed Three-Dimensional Building Façade Reconstruction: A Review on Applications, Data and Technologies

“…Due to the adoption of crowd-sourcing, many nonexperts can now share geospatial data. For example, Fan et al [73] designed an integrated platform to reconstruct 3D building models based on images collected by volunteers or non-expert users. The results appear promising for delivering more detailed building models, however, no information on the location accuracy was reported.…”

“…Rules play an important role in detailed façade reconstruction as openings follow architectural rules concerning their shape and spatial relationships (e.g., the locations of windows and doors relative to walls). Rules can be applied to openings extracted from corner detectors [9,107], a graph model [73], machine learning [108] or based on the assumption of symmetry in window distribution [109].…”

“…To address this problem, Fan et al [73] proposed façade layout graph model method based on Gestalt [111] principles and the principle of architectural form [112]. Although the proposed method describes different types of façade structures, its applicability for complex structures and automation needs further improvements.…”

Combining Visibility Analysis and Deep Learning for Refinement of Semantic 3d Building Models by Conflict Classification

“…When analyzing laser observations, openings are often assumed to represent holes due to their translucent characteristic or faceintruded position (Tuttas and Stilla, 2013;Fan et al, 2021). For example, windows are detected based on building interior points, which imply opening existence (Tuttas and Stilla, 2013).…”