3d Building Reconstruction From Lidar Point Clouds by Adaptive Dual Contouring

Abstract

ABSTRACT:This paper presents a novel workflow for data-driven building reconstruction from Light Detection and Ranging (LiDAR) point clouds. The method comprises building extraction, a detailed roof segmentation using region growing with adaptive thresholds, segment boundary creation, and a structural 3D building reconstruction approach using adaptive 2.5D Dual Contouring. First, a 2D-grid is overlain on the segmented point cloud. Second, in each grid cell 3D vertices of the building model are estimated from the corresponding LiDAR points. Then, the number of 3D vertices is reduced in a quad-tree collapsing procedure, and the remaining vertices are connected according to their adjacency in the grid. Roof segments are represented by a Triangular Irregular Network (TIN) and are connected to each other by common vertices or -at height discrepancies -by vertical walls. Resulting 3D building models show a very high accuracy and level of detail, including roof superstructures such as dormers. The workflow is tested and evaluated for two data sets, using the evaluation method and test data of the "ISPRS Test Project on Urban Classification and 3D Building Reconstruction" (Rottensteiner et al., 2012). Results show that the proposed method is comparable with the state of the art approaches, and outperforms them regarding undersegmentation and completeness of the scene reconstruction.

Automatic 3-D Building Model Reconstruction from Very High Resolution Stereo Satellite Imagery

“…Most of the efforts in data-driven roof model reconstruction have been focused on the roof plane segmentation [21,50,51]. The point cloud segmentation methods, such as surface growing [29], triangulation irregular network (TIN) growing [46,52], and surface fitting techniques [53], turn roof surface points into planar, cylindrical, and spherical structures [54]. After detecting the roof segment regions, the adjacency between them is determined based on the closeness of two segments features such as edges [50], points [55], and intersection lines [22].…”

Aerial LiDAR Data Augmentation for Direct Point-Cloud Visualisation

“…The approach uses graph-theory to represent the topological building structure, separates the buildings into different parts according to their topological relationship and reconstructs the building model by joining individual models using graph matching. An approach to 3D building reconstruction [12] uses adaptive 2.5D dual contouring. For each cell in a 2D grid overlaid on top of the LiDAR point-cloud data, vertices of the building model are estimated and their number is reduced using quad-tree collapsing procedures.…”

A greyscale voxel model for airborne lidar data applied to building detection

“…(1) Region growing. This initially identifies seeds located on planar surface patches and then enlarges these patches around the seeds using smoothness constraints, curvature consistency or other similarity criteria (Morgan and Habib, 2002;Orthuber and Avbelj, 2015;Vo et al, 2015;Gilani et al, 2016;Wang et al, 2017).…”