Quality control and progress monitoring from large-scale 3D point clouds

点击翻译按钮获取中文摘要

The advent of new 3D sensors clearly marks a revolution for the infrastructure and construction industry, but they also come with their own set of issues. One of the simplest ways to summarize most of these is by stressing the important distinction between gathering and using data. The main problem faced by construction and infrastructure companies has shifted from data acquisition to data interpretation. One example of such a transition is the as-built vs. as-design comparison. The mere task of aligning these 3D modalities (CAD models and high density point clouds) is challenging because of the incompleteness, noise, discrepancies, and occlusions that inevitably occur in any real-world 3D capture. In addition, there may exist structural differences between the CAD model and the point cloud (that is the point of comparing them), which further complicates their alignment.The main goal of this project is to provide tools to engineers, architects, designers, inspectors, surveyors, and other professionals to assist them in tedious and time-consuming tasks related to the exploitation of those new sensors and techniques. By designing systems able to intelligently clean, pre-process and interpret a 3D representation embedded in a raw point cloud within specific professional contexts, to point out potential problematic situations before they even occur, and to produce helpful abstractions to better assess a situation, it will be possible to reduce the workload and improve the efficiency of the professionals overseeing construction sites. In turn, this will lead to cost reductions and new possibilities such as more frequent surveys, increasing the chances of early error catching and reducing the risk of cost and time overruns. This could also have an impact on the safety and security of workers.