Segmentation of Planar Surfaces from Laser Scanning Data Using the Magnitude of Normal Position Vector for Adaptive Neighborhoods

Abstract

Diverse approaches to laser point segmentation have been proposed since the emergence of the laser scanning system. Most of these segmentation techniques, however, suffer from limitations such as sensitivity to the choice of seed points, lack of consideration of the spatial relationships among points, and inefficient performance. In an effort to overcome these drawbacks, this paper proposes a segmentation methodology that: (1) reduces the dimensions of the attribute space; (2) considers the attribute similarity and the proximity of the laser point simultaneously; and (3) works well with both airborne and terrestrial laser scanning data. A neighborhood definition based on the shape of the surface increases the homogeneity of the laser point attributes. The magnitude of the normal position vector is used as an attribute for reducing the dimension of the accumulator array. The experimental results demonstrate, through both qualitative and quantitative evaluations, the outcomes’ high level of reliability. The proposed segmentation algorithm provided 96.89% overall correctness, 95.84% completeness, a 0.25 m overall mean value of centroid difference, and less than 1° of angle difference. The performance of the proposed approach was also verified with a large dataset and compared with other approaches. Additionally, the evaluation of the sensitivity of the thresholds was carried out. In summary, this paper proposes a robust and efficient segmentation methodology for abstraction of an enormous number of laser points into plane information.

Fast Edge Detection and Segmentation of Terrestrial Laser Scans Through Normal Variation Analysis

“…Su et al (2016) present a segmentation algorithm for industrial sites where an octree-based split is performed based on a graph theory based analysis and a combination of proximity, orientation, and curvature connectivity criteria is used for a merging process. Kim et al (2016) propose a segmentation of planar surfaces using the magnitude of normal position vector for a cylindrical neighbor, which uses two sets of best-fitting plane parameters against two origins as attributes. Lastly, Hackel et al (2016) propose an efficient method of semantic classification and demonstrate the effectiveness using both TLS and MLS data.…”

Automatic Room Segmentation of 3D Laser Data Using Morphological Processing

“…Table 5 lists the evaluation metrics computed by the five existing methods and our approach using the 20 publicly available data sets without and with furniture. = total number of pixels matched total number of pixels detected automatically (2) = total number of pixels matched total number of pixels detected manually Finally, quantitative evaluations are carried out using three different measures: correctness, completeness, and absolute deviation [40,43]. The correctness and completeness measures were calculated pixel-by-pixel in comparing the automatically segmented map with the ground truths.…”

“…This was attributable to the inability of the detection window in the initial segmentation phase to pass through the areas where there were lots of occlusions, thus resulting in over-production of the initial segments. Finally, quantitative evaluations are carried out using three different measures: correctness, completeness, and absolute deviation [40,43]. The correctness and completeness measures were calculated pixel-by-pixel in comparing the automatically segmented map with the ground truths.…”

“…The diffused noisy points were mainly due to a mirror in the scan area [39]. To enhance the current noise-filtering phase, one possible means would be planar detection [40], which will be the focus of one of our future studies. Additionally, we evaluated our room segmentation approach, as shown in Figure 15, using four publicly available point-cloud data sets [41].…”

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

“…(3) Clustering. This method first associates each lidar point with a feature vector, which consists of geometric and/or radiometric measures and then segments lidar points in feature spaces by a clustering technique such as k-means, maximum likelihood or fuzzy clustering (Filin, 2002;Hofmann, 2004;Vosselman et al, 2004;Filin and Pfeifer, 2006;Sun and Salvaggio, 2013;Kong et al, 2014;Zhao et al, 2014;Song et al, 2015;He et al, 2016;Kim et al, 2016;Cao et al, 2017). (4) Filtering.…”