Efficient RANSAC for Point‐Cloud Shape Detection

Abstract

In this work we present an automatic algorithm to detect basic shapes in unorganized point clouds. The algorithm decomposes the point cloud into a concise, hybrid structure of inherent shapes and a set of remaining points. Each detected shape serves as a proxy for a set of corresponding points. Our method is based on random sampling and detects planes, spheres, cylinders, cones and tori. For models with surfaces composed of these basic shapes only, e.g. CAD models, we automatically obtain a representation solely consisting of shape proxies. We demonstrate that the algorithm is robust even in the presence of many outliers and a high degree of noise. The proposed method scales well with respect to the size of the input point cloud and the number and size of the shapes within the data. Even point sets with several millions of samples are robustly decomposed within less than a minute. Moreover the algorithm is conceptually simple and easy to implement. Application areas include measurement of physical parameters, scan registration, surface compression, hybrid rendering, shape classification, meshing, simplification, approximation and reverse engineering.

Autonomous Point Cloud Acquisition of Unknown Indoor Scenes

“…The normal vector of each wall was calculated taking into consideration the horizontal section of the point cloud at a certain distance below the ceiling and based on a random sample consensus (RANSAC) algorithm [32]. As a result, the dominant plane of each wall and its points were obtained.…”

Görüntü ve lidar verisinden bina tespitinde farkli yöntemler

“…Bunun için RANSAC algoritması [14] ile düzlemler tespit edilmiş ve düzlemsellik göstermeyen nesneler göz ardı edilmiştir.…”

Pipe-Run Extraction and Reconstruction from Point Clouds

“…For instance, Schnabel et al [23] present an efficient RANSAC approach to detect primitive shapes from point clouds. Hofer et al [13] adopt line geometry for the recognition and reconstruction of 3D surfaces.…”

“…2. Given a real-world scan of industrial structures (a), we show 3D reconstruction results from different approaches: (b) extracted pipe axis network by our approach, (c) reconstructed pipe-runs by our approach, (d) Ball-Pivoting Algorithm [2], (e) RANSAC algorithm [23], and (f) GlobFit [18] 2 Related Work…”

“…Another strategy of reconstruction attempts to fit primitives (e.g., cylinders, spheres and planes) to the raw data, capturing geometric information conveyed in the input points (e.g., [11,24,23]). This strategy is well-suited to industrial sites since most parts of them are composed of primitive shapes ( [12,20,21]).…”