Abstract
Abstract. Ground objects can be regarded as a combination of structures of different geometries. Generally, the structural geometries can be grouped into linear, planar and scatter shapes. A good segmentation of objects into different structures can help to interpret the scanned scenes and provide essential clues for subsequent semantic interpretation. This is particularly true for the terrestrial static and mobile laser scanning data, where the geometric structures of objects are presented in detail due to the close scanning distances. In consideration of the large data volume and the large variation in point density of such point clouds, this paper presents a structural segmentation method of point clouds to efficiently decompose the ground objects into different structural components based on supervoxels of multiple sizes. First, supervoxels are generated with sizes adaptive to the point density with minimum occupied points and minimum size constraints. Then, the multi-size supervoxels are clustered into different components based on a structural labelling result obtained via Markov random field. Two datasets including terrestrial and mobile laser scanning point clouds were used to evaluate the performance of the proposed method. The results indicate that the proposed method can effectively and efficiently classify the point clouds into structurally meaningful segments with overall accuracies higher than 96%, even with largely varying point density.
Highlights
Mobile laser scanning (MLS) and static terrestrial laser scanning (TLS) point clouds can intuitively present the threedimensional (3D) geometric characteristics of ground objects with abundant details
The Semantic3D point cloud dataset is acquired by a static TLS system and has very high but relatively consistent point density
The structural segmentation results of the two datasets with the proposed method are shown and the results are compared to the results based on supervoxel generated by other methods, including the voxel cloud connectivity segmentation (VCCS) (Papon et al, 2013) and toward better boundary preserved (TBBP) (Lin et al, 2018)
Summary
Mobile laser scanning (MLS) and static terrestrial laser scanning (TLS) point clouds can intuitively present the threedimensional (3D) geometric characteristics of ground objects with abundant details These detailed structures of objects can be grouped into linear, planar and scatter shapes that can be described by the eigenvalues derived from the covariance matrix of local neighbourhoods (Hackel et al, 2016; Landrieu et al, 2017; Liu and Boehm, 2015; Weinmann et al, 2014, 2017; Yang et al, 2015). ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume IV-2/W5, 2019 ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands local geometric properties of different shapes, this paper proposed a coarse-to-fine supervoxel segmentation method based on an octree structure, which is built under constraints about the minimum number of points occupied by a supervoxel and the minimum resolution of supervoxels. Two experiments with different datasets were carried out to evaluate the performance of the proposed method and discussions and conclusions were drawn at last based on the experimental results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
