Abstract
Abstract. This paper presents a data-driven workflow for the detection of scaffolding components from point clouds. The points belonging to the scaffolding components are identified and separated from the main building structures and two basic elements, namely the toeboard and the tube, are reconstructed. The workflow has four main processing steps. Firstly, the raw point clouds are preprocessed by statistical filtering and voxel girding. In the second step, the planar surfaces of the building surface and scaffoldings are extracted via RANSAC and then grouped by their parallelity and distance to separate the building façade. In the third step, the 3D shape descriptor FPFH and random forest classification algorithm are applied to classify the point data of building façades into classes belonging to different elements. Finally, by the use of linear fitting algorithm and matching using SHOT shape descriptor, the tubes and toeboards are reconstructed with their geometric parameters. It is shown that the points belonging to these objects are identified and then reconstructed with cylinder and cuboid models. The final results show that over 60% of the tubes and nearly 90% of the toeboards are reconstructed in the investigated façade, and more than 40% of the reconstructed objects are well rebuilt.
Highlights
1.1 MotivationIn the fields of Architecture, Engineering and Construction/ Facility Management (AEC/FM), the demand for efficient and accurate progress monitoring of construction site has dramatically grown in recent decades for popular specialized applications in work progress control, productivity improvement, security assurance, accident investigation, collaborative communications, etc. (Turkan et al, 2012).Normally, traditional progress tracking approaches depend highly on visual inspection and require extensive manual collection of data and analysis of various documents
The purpose of this work is to detect and reconstruct the scaffolding components from photogrammetric point cloud generated by stereo matching of a construction site with complex environment, in order to make a good preparation for the further rebuilding of as-built BIM and provide auxiliary information on the monitoring of the construction process
Afterwards, a 3D shape descriptor: fast point feature histogram (FPFH) is applied to the point data of building façades in order to obtain the features of different elements
Summary
Traditional progress tracking approaches depend highly on visual inspection and require extensive manual collection of data and analysis of various documents Such progress monitoring methods rely heavily on the personal skills and the experiences of professionals and and require a lot of time. To solve this problem, the automatic construction site monitoring is developed with the application of 2D imaging, photogrammetry and Terrestrial Laser Scanning (TLS) in recent years (Turkan et al, 2012). Since the scaffolds are commonly used to assist the construction and the maintenance of buildings, by judging the status of the reconstructed scaffolds, the professionals can make an appropriate evaluation of the aggregate scheduling for the construction project
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
