FuzzyPSReg: Strategies of Fuzzy Cluster-Based Point Set Registration

Abstract

This article studies the fuzzy cluster-based point set registration (FuzzyPSReg). First, we propose a new metric based on Gustafson–Kessel (GK) fuzzy clustering to measure the alignment of two point clouds. Unlike the metric based on fuzzy c-means (FCM) clustering in our previous work, the GK-based metric includes orientation properties of the point clouds, thereby providing more information for registration. We then develop the registration quality assessment of the GK-based metric, which is more sensitive to small misalignments than that of the FCM-based metric. Next, by effectively combining the two metrics, we design two FuzzyPSReg strategies with global optimization. 1) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FuzzyPSReg-SS</i> , which extends our previous work and aligns two similar-sized point clouds with greatly improved efficiency. 2) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FuzzyPSReg-O2S</i> , which aligns two point clouds with a relatively large difference in size and can be used to estimate the pose of an object in a scene. In the experiment, we use different point clouds to test and compare the proposed method with state-of-the-art registration approaches. The results demonstrate the advantages and effectiveness of our method.