Coarse Alignment for Model Fitting of Point Clouds Using a Curvature-Based Descriptor

Abstract

This paper presents a method for coarse alignment of point clouds by introducing a new descriptor based on the local curvature. The method is developed for model fitting a CAD model for use in robotic assembly. The method is based on selecting keypoints depending on shape factors calculated from the local covariance matrix of the surface. A descriptor is then calculated for each keypoint by fitting two spheres that describe the curvature of the surface. The spheres are calculated using conformal geometric algebra, which gives a convenient and efficient description of the geometry. The keypoint descriptors for the model and the observed point cloud are then compared to estimate the corresponding keypoints, which are used to calculate the displacement. The method is tested in several experiments. One experiment is for robotic assembly, where objects are placed on a table and their position and orientation is estimated using a 3D CAD model.

A Curvature-Based Descriptor for Point Cloud Alignment Using Conformal Geometric Algebra

“…The method proposed in [15] generates a set of descriptors based on the following steps: first a set of keypoints are found in both the model point cloud X and the observation point cloud Y , X keypoints and Y keypoints respectively. This is done by generating a local reference frame at each point using PCA, and selecting the points which have a unique geometry based on their shape factors.…”

“…As proposed in [15], two spheres are generated to represent the curvature of the surface at each keypoint. This is done based on the the sphere fitting method presented in Sect.…”

“…In [15] we proposed a course registration method where keypoints were selected based on the local surface around each point. A descriptor was then calculated for each keypoint by fitting two spheres to the surface around the keypoint.…”

“…In this paper we propose an improvement to the descriptor in [15] where a new and improved descriptor is used, based on a geometric approach. The main improvement of the method is that more keypoint correspondences are found, which improves the estimation of the displacement.…”

“…2 presents the methods and notation used in the paper, including the required background in conformal geometric algebra. Section 3 describes the method proposed in [15] as well as the improvement proposed in this paper. Section 4 presents the experimental, which demonstrates the successful application of the method.…”