Reconstruction of Polygonal Faces from Large-Scale Point-Clouds of Engineering Plants

ABSTRACTThe recent progress of mid-range and long-range laser scanners makes it possible to capture dense point-clouds of manufacturing plants. 3D models of manufacturing plants are useful for simulating the reorganizing of production lines. Since point-clouds are not structured and very large, it is often required to convert point-clouds into more concise models. So far, researchers have studied shape reconstruction of pipe structures by detecting cylindrical surfaces and estimating the lengths of the cylinders. On the other hand, few researches have discussed to extract polygonal faces from large-scale point-clouds. Planar faces may have very complicated boundaries, because point-clouds are noisy and often occluded by other surfaces in manufacturing plants. In this paper, we propose an efficient method for constructing simplified polygonal faces from large-scale point-clouds. In our method, we map each point-cloud onto a 2D image and detect bounded planar faces in the 2D image. Our method allows us to c...