Fully automated as-built 3D pipeline segmentation based on curvature computation from laser-scanned data

초록

There has been a growing demand for the three-dimensional (3D) reconstruction of as-built pipeline. The as-built 3D pipeline reconstruction process consists of measurement of the plant facility, identification of the pipelines, and generation of the 3D pipeline model. Although measurement is now efficiently performed using laser-scanning technology and there has been much progress in 3D pipeline model generation, identification of the pipelines from large and complex sets of laser-scanned data remains a challenging problem. The aim of this study is to propose an as-built 3D pipeline segmentation approach to automatically identify as-built pipelines. The steps of the proposed approach are segmentation of the 3D point cloud, feature extraction based on curvature computation, and pipeline classification. The experiment was performed at an operating plant in order to validate the proposed approach. The experimental result revealed that the proposed method can indeed contribute to the automation of as-built 3D pipeline reconstruction.

키워드