Name
Abstract | ||
|---|---|---|
Building facades can feature different patterns depending on the architectural style, functionality, and size of the buildings; therefore, reconstructing these facades can be complicated. In particular, when semantic facades are reconstructed from point cloud data, uneven point density and noise make it difficult to accurately determine the facade structure. When investigating facade layouts, Gestalt principles can be applied to cluster visually similar floors and facade elements, allowing for a more intuitive interpretation of facade structures. We propose a novel model for describing facade structures, namely the layout graph model, which involves a compound graph with two structure levels. In the proposed model, similar facade 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 facade reconstruction to an optimization strategy using simulated annealing coupled with Gibbs sampling. Multiple facade 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 facades and qualities of point cloud data, enabling a more robust and accurate reconstruction of facade models. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1080/10095020.2021.1922316 | GEO-SPATIAL INFORMATION SCIENCE |
Keywords | DocType | Volume |
Building faç, ade, semantic reconstruction, point cloud, compound graph model, stochastic process | Journal | 24 |
Issue | ISSN | Citations |
3 | 1009-5020 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hongchao Fan | 1 | 17 | 7.44 |
| Yuefeng Wang | 2 | 0 | 0.68 |
| Jianya Gong | 3 | 541 | 57.06 |