Abstract
Abstract. This paper presents an automated and effective method for detecting planes and their intersections as edges in unorganized point clouds. The edges are subsequently extracted as vectors to a CAD environment. The software was developed within the Microsoft Visual Studio and the open source Point Cloud Library (PCL, http://pointclouds.org/) was used. The Point Cloud Library is a standalone, large scale, open project for 2D/3D image and point cloud processing. The code was written in C++. For the detection of the planes in the point cloud the RANSAC algorithm was employed. Subsequently, and according to the standard theory of Analytic Geometry the edges were determined as the intersections of these planes with each other. A straight line in 3D space is defined by one of its points, which was determined with the Lagrangian Multipliers method and a parallel vector, which was determined with the help of the cross product of two vectors on space. Finally, the algorithm and the results of the implementation of the process with real data were evaluated by performing various checks, mainly aiming to determine the accuracy of the edge detection.
Highlights
Nowadays, with the advancement and the popularity of Image Based Modelling, and with the increasing use of terrestrial laser scanning an infinite number of point clouds are acquired, especially for the geometric documentation of cultural heritage artifacts and monuments (Kersten et al 2009, Tryfona & Georgopoulos, 2016)
With the goal of fully or partially automated linear vector extraction from unorganized point clouds, the current study aims to locate planes in order to determine their intersections and extract them as edges, i.e. vector lines, of the depicted object to which these planes belong
The first test was carried out in the point cloud of the planes depicted in red in figure 5
Summary
With the advancement and the popularity of Image Based Modelling, and with the increasing use of terrestrial laser scanning an infinite number of point clouds are acquired, especially for the geometric documentation of cultural heritage artifacts and monuments (Kersten et al 2009, Tryfona & Georgopoulos, 2016). Certain researchers (Rodríguez Miranda et al 2008, Canciani et al 2013, Azariadis & Sapidis 2005) have tried to produce vector shapes, i.e. mainly linear features, directly from the point clouds either manually or semi-automatic. Several efforts have been published so far for that task with varying degrees of success (Huang et al 2003, Vosselmann et al 2003, Lu et al 2008, Yu et al 2015) Their main purpose has been to detect straight edges in the point clouds, which is one of the most important issues in the area of image processing and computer vision, and which has been studied for years. The rest of the paper is organized as follows: Section 2 explains the point clouds, Section 3 shows the proposed methodology, Section 4 reveals the results and Section 5 exposes the conclusions
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
