Efficient building instance segmentation is necessary for many applications such as parallel reconstruction, management and analysis. However, most of the existing instance segmentation methods still suffer from low completeness, low correctness and low quality for building instance segmentation, which are especially obvious for complex building scenes. This paper proposes a novel unsupervised building instance segmentation (UBIS) method of airborne Light Detection and Ranging (LiDAR) point clouds for parallel reconstruction analysis, which combines a clustering algorithm and a novel model consistency evaluation method. The proposed method first divides building point clouds into building instances by the improved kd tree 2D shared nearest neighbor clustering algorithm (Ikd-2DSNN). Then, the geometric feature of the building instance is obtained using the model consistency evaluation method, which is used to determine whether the building instance is a single building instance or a multi-building instance. Finally, for multiple building instances, the improved kd tree 3D shared nearest neighbor clustering algorithm (Ikd-3DSNN) is used to divide multi-building instances again to improve the accuracy of building instance segmentation. Our experimental results demonstrate that the proposed UBIS method obtained good performances for various buildings in different scenes such as high-rise building, podium buildings and a residential area with detached houses. A comparative analysis confirms that the proposed UBIS method performed better than state-of-the-art methods.

The generation of a concise building model has been and continues to be a challenge in photogrammetry and computer graphics. The current methods typically focus on the simplicity and fidelity of the model, but those methods either fail to preserve the structural information or suffer from low computational efficiency. In this paper, we propose a novel method to generate concise building models from dense meshes by extracting and completing the planar primitives of the building. From the perspective of probability, we first extract planar primitives from the input mesh and obtain the adjacency relationships between the primitives. Since primitive loss and structural defects are inevitable in practice, we employ a novel structural completion approach to eliminate linkage errors. Finally, the concise polygonal mesh is reconstructed by connectivitybased primitive assembling. Our method is efficient and robust to various challenging data. Experiments on various building models revealed the efficacy and applicability of our method.

3D plane segmentation has been and continues to be a challenge in 3D point cloud processing. The current methods typically focus on the planar subsets separation but ignore the requirement of the precise plane fitting. We propose a quasi-acontrario theory-based plane segmentation (QTPS) algorithm, which is capable of dealing with point clouds of severe noise level, low density, and high complexity robustly. The main proposition is that the final plane can be composed of basic planar subsets with high planar accuracy. We cast planar subset extraction from the point set as a geometric rigidity measuring problem. The meaningfulness of the planar subset is estimated by the number of false alarms (NFA), which can be used to eliminate false-positive effectively. Experiments were conducted to analyze both the planar subset extraction and the 3D plane segmentation. The results show that the proposed algorithms perform well in terms of accuracy and robustness compared with state-of-art methods. Experimental datasets, results, and executable program of the proposed algorithm are available at https://skyearth.org/publication/project/QTPS.