13 February 2023 in IEEE Sensors Journal
An efficient method based on plane segmentation and projection is proposed to extract as complete boundary (straight) line segments as possible. To efficiently detect boundary points, 3D planar point clouds (patches) generated by plane segmentation are converted into 2D images by graphical projection to avoid point-based nearest neighbors searching. To preserve boundary details, the projection resolution for each plane is determined through accurate statistics of average local intervals between points in voxels composing corresponding planar point clouds. To alleviate erroneous line segmentation extraction caused by uneven densities of planar point clouds, improved mathematical morphological operation, whose structural element order is self-adaptive to local point density, is proposed for crack inpainting of projected images. As for extraction of 3D boundary line segments, the back-projection results of 2D boundary line segments detected from images are utilized as references for clustering of boundary points, and a 3D straight line fitting algorithm based on recursive weighted least squares is employed to reduce the effect of boundary noise. A series of refinement strategies are further presented to control the quality of extracted 3D line segments. Experimental results demonstrate that the proposed line segment extraction method can provide efficient and fine processing results as well as automatic processing ability, which satisfies the efficient processing demand for large-scale point clouds.
7 April 2026 in IEEE Sensors Journal
Point cloud based 3D reconstruction is a critical technique for urban digitalization. Traditional marker-based methods involve deploying targets, which are time-consuming, inefficient, and sometimes fail to ensure accurate registration. Given the abundance of linear features in urban environments, leveraging line features for automatic registration of urban point clouds offers a promising solution. However, individual linear features lack sufficient information to support robust correspondence establishment. Therefore, we propose a Semantic Structure Based Registration (SSBR) method that utilizes line segment tuples as semantic structures. The method first extracts line features from point clouds using edge line detection algorithms, yielding a set of line segments along with their endpoints and support regions. It then identifies semantic structures from building facades and extracts their semantic attributes. Next, semantic structures are matched pairwise based on similarity measurements, and corresponding transformations are computed. The result with the highest number of common line segments is selected as the initial registration outcome. Finally, registration refinement is achieved through alignment of common line segments. Experimental results on three urban point cloud datasets demonstrate that the proposed SSBR method enables efficient and automatic registration of large-scale urban point clouds with centimeter-level accuracy. Compared with baseline approaches, the SSBR method shows superior overall performance across different datasets.