GCSAC: geometrical constraint sample consensus for primitive shapes estimation in 3D point cloud

Abstract

Estimating parameters of a primitive shape from a point cloud data is a challenging problem due to the data containing noises and computational time demand. In this paper, we present a new robust estimator (named GCSAC, geometrical constraint sample consensus) aimed at solving such issues. The proposed algorithm takes into account geometrical constraints to construct qualified samples for the estimation. Instead of randomly drawing minimal subset of sample, explicit geometrical properties of the interested primitive shapes (e.g., cylinder, sphere and cone) are used to drive the sampling procedures. Based on the collected samples, model estimation and verification procedures of the robust estimator are deployed in GCSAC. Extensive experiments are conducted on synthesised and real datasets. Comparing with the common algorithms of RANSAC family, GCSAC outperforms in term of both the precision of the estimated model and computational time. The implementations of GCSAC and the datasets are made publicly available.