Cylinders extraction in non-oriented point clouds as a clustering problem

Abstract

Finding geometric primitives in 3D point clouds is a fundamental task in many engineering applications such as robotics, autonomous-vehicles and automated industrial inspection. Among all solid shapes, cylinders are frequently found in a variety of scenes, comprising natural or man-made objects. Despite their ubiquitous presence, automated extraction and fitting can become challenging if performed "in-the-wild", when the number of primitives is unknown or the point cloud is noisy and not oriented.In this paper we pose the problem of extracting multiple cylinders in a scene by means of a Game-Theoretic inlier selection process exploiting the geometrical relations between pairs of axis candidates. First, we formulate the similarity between two possible cylinders considering the rigid motion aligning the two axes to the same line. This motion is represented with a unitary dual-quaternion so that the distance between two cylinders is induced by the length of the shortest geodesic path in SE(3). Then, a Game-Theoretical process exploits such similarity function to extract sets of primitives maximizing their inner mutual consensus. The outcome of the evolutionary process consists in a probability distribution over the sets of candidates (ie axes), which in turn is used to directly estimate the final cylinder parameters. An extensive experimental section shows that the proposed algorithm offers a high resilience to noise, since the process inherently discards inconsistent data. Compared to other methods, it does not need point normals and does not require a fine tuning of multiple parameters.

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

“…It can show the change information of the vertices. Literature [ 21 , 22 ] summarizes the current research status of human motion recognition, including video-based, sensor-based, and radio-frequency-based research status. Literature [ 23 ] analyzed the basic principles of CNN and established a structure based on CNN.…”

Towards automatic digital documentation and progress reporting of mechanical construction pipes using smartphones

“…Once the ellipses are detected, an initial estimate of the cylinder's axis, radius and center can provide a set of isolated points of interest to be fed to the robust cylinder detection of [4]. To acquire the cylinder's axis from equation 3, however, the normal vector must be rotated either +𝛿𝛿 or −𝛿𝛿 along the semi-minor axis [57] (two-fold ambiguity). Therefore, both possible solutions are first used to generate isolated interest points for each cylinder.…”

New confocal hyperbola-based ellipse fitting with applications to estimating parameters of mechanical pipes from point clouds

“…In three-dimensional point clouds, the intersection of spheres, cones, and cylinders with a plane also delivers points following an elliptic pattern. Reliable and accurate ellipse fitting to data is, hence, commonly an important step towards solving various real-world applications pertaining to shapes such as circles, cylinders and spheres, including, galaxy classification [1], traffic sign detection [2], phase estimation in interferograms [3], cell segmentation in fluorescence microscopy images [4], demodulation of interferometer signals [5], terrestrial laser scanner (TLS) registration [6], optical instrument calibration [7], geometric as-built building information modeling (BIM) of pipes [8], cylinder fitting of industrial shapes [9], and cylindrical point cloud classification [10].…”