Segmentation of LiDAR Data Using Multilevel Cube Code

Abstract

Light detection and ranging (LiDAR) data collected from airborne laser scanning systems are one of the major sources of spatial data. Airborne laser scanning systems have the capacity for rapid and direct acquisition of accurate 3D coordinates. Use of LiDAR data is increasing in various applications, such as topographic mapping, building and city modeling, biomass measurement, and disaster management. Segmentation is a crucial process in the extraction of meaningful information for applications such as 3D object modeling and surface reconstruction. Most LiDAR processing schemes are based on digital image processing and computer vision algorithms. This paper introduces a shape descriptor method for segmenting LiDAR point clouds using a “multilevel cube code” that is an extension of the 2D chain code to 3D space. The cube operator segments point clouds into roof surface patches, including superstructures, removes unnecessary objects, detects the boundaries of buildings, and determines model key points for building modeling. Both real and simulated LiDAR data were used to verify the proposed approach. The experiments demonstrated the feasibility of the method for segmenting LiDAR data from buildings with a wide range of roof types. The method was found to segment point cloud data effectively.

Comparison of LiDAR Building Point Cloud with Reference Model for Deep Comprehension of Cloud Structure

“…The average values of RMSE are between 1.25 m and 0.5 m. Demir (2018) compares the shifts in X, Y and Z coordinates of roof vertices. Akca et al (2010), Dorninger and Pfeifer (2008), Erberink and Vossleman (2011), Ostrowski et al (2018), Park et al (2019), Sampath and Shan (2010), Tarsha and Tarsha Kurdi et al (2019) suggest using the Lidar point cloud as the reference data.…”

“…In this context, the accuracy estimation methods suggested in the literature can be classified into two categories. The first one uses the point cloud as a reference model such as Akca et al (2010), Dorninger and Pfeifer (2008), Erberink and Vossleman (2011), Ostrowski et al (2018), Park et al (2019) and Sampath and Shan (2010). The approaches of the second category employ 3D reference models calculated from areal images or reference measurements in the field (Gülch, et al 2018, Jung and Sohn, 2018, Rottensteiner et al 2014and Kaartinen et al 2005.…”

Automatic filtering and 2D modeling of airborne laser scanning building point cloud

“…First, Tarsha Kurdi, Awrangjeb, and Munir (2019) calculate the building digital surface model (DSM) by resembling that removes the undesirable points related to vertical elements such as building facades. Sometimes this operation does not eliminate all these points, which is why Park, Lee, Yoo, and Lee (2019) eliminate the unnecessary objects by applying the cube operator to segment the building point cloud into roof surface patches, including superstructures, removing unnecessary objects, detecting the boundaries of buildings, and determining the model key points for building modeling.…”

“…In order to estimate the accuracy of building models calculated from LiDAR data, Dorninger and Pfeifer (2008), Akca, Freeman, Sargent, and Gruen (2010), Sampath and Shan (2010), Elberink and Vossleman (2011), Park et al (2019), and Tarsha Kurdi et al (2019) suggest using the LiDAR point cloud as reference data. This choice has been adopted because it allows the study of deformation generated only by the modeling algorithm, independent of the quality of the input building point cloud.…”

Automatic evaluation and improvement of roof segments for modelling missing details using Lidar data

“…2008),Dorninger and Pfeifer (2008),Ostrowski et al (2018), Erberink and Vossleman (2011),Akca et al (2010),Sampath and Shan (2010) andPark et al (2019). Consequently, one of the crucial elements of their approaches of modelling accuracy estimation is the calculation of distances (point per point) between the 3D building model and the point cloud.…”