Recognition of complex engineering objects from large-scale point clouds

Abstract This work was aimed at reconstructing the structural model of as-built industrial facilities like plants purely from on-site point cloud measurement data. Focus was set on finding the internal structure of complex objects hidden behind the massive point cloud by exploiting connectivity information in the data and the linear characteristics of the typical components. A workflow is presented with emphasis on data filtering, connectivity graph construction, as well as the recognition of elementary objects and their relations. Results are demonstrated using data of an industrial case study.