In machine vision typical heuristic methods to extract parameterized objects out of raw data points are the Hough transform and RANSAC. Bayesian models carry the promise to optimally extract such parameterized objects given a correct definition of the model and the type of noise at hand. A category of solvers for Bayesian models are Markov chain Monte Carlo methods. Naive implementations of MCMC methods suffer from slow convergence in machine vision due to the complexity of the parameter space. Towards this blocked Gibbs and split-merge samplers have been developed that assign multiple data points to clusters at once. In this paper we introduce a new split-merge sampler, the triadic split-merge sampler, that perform steps between two and three randomly chosen clusters. This has two advantages. First, it reduces the asymmetry between the split and merge steps. Second, it is able to propose a new cluster that is composed out of data points from two different clusters. Both advantages speed up convergence which we demonstrate on a line extraction problem. We show that the triadic split-merge sampler outperforms the conventional split-merge sampler. Although this new MCMC sampler is demonstrated in this machine vision context, its application extend to the very general domain of statistical inference.@en

Line detection is a fundamental problem in the world of computer vision. Many sophisticated methods have been proposed for performing inference over multiple lines; however, they are quite ad-hoc. Our fully Bayesian model extends a linear Bayesian regression model to an infinite mixture model and uses a Dirichlet Process as a prior. Gibbs sampling over non-unique parameters as well as over clusters is performed to fit lines of a fixed length, a variety of orientations, and a variable number of data points. Bayesian inference over data is optimal given a model and noise definition. Initial computer experiments show promising results with respect to clustering performance indicators such as the Rand Index, the Adjusted Rand Index, the Mirvin metric, and the Hubert metric. In future work, this ematical foundation can be used to extend the algorithms to inference over multiple line segments and multiple volumetric objects.

@en

In computer and robotic vision point clouds from depth sensors have to be processed to form higher-level concepts such as lines, planes, and objects. Bayesian methods formulate precisely prior knowledge with respect to the noise and likelihood of points given a line, plane, or object. Nonparametric methods also formulate a prior with respect to the number of those lines, planes, or objects. Recently, a nonparametric Bayesian method has been proposed to perform optimal inference simultaneously over line fitting and the number of lines. In this paper we propose a nonparametric Bayesian method for segment fitting. Segments are lines of finite length. This requires 1.) a prior for line segment lengths: the symmetric Pareto distribution, 2.) a sampling method that handles nonconjugacy: an auxiliary variable MCMC method. Results are measured according to clustering performance indicators, such as the Rand Index, the Adjusted Rand Index, and the Hubert metric. Surprisingly, the performance of segment recognition is worse than that of line recognition. The paper therefore concludes with recommendations towards improving Bayesian segment recognition in future wo@en

In computer vision there are many sophisticated methods to perform inference over multiple lines, however they are quite ad-hoc. In this paper a fully Bayesian approach is used to fit multiple lines to a point cloud simultaneously. Our model extends a linear Bayesian regression model to an infinite mixture model and
uses a Dirichlet process as a prior for the partition. We perform Gibbs sampling over non-unique parameters as well as over clusters to fit lines of a fixed length, a variety of orientations, and a variable number of data points. The performance is measured using the Rand Index, the Adjusted Rand Index, and two other clustering performance indicators. This paper is mainly meant to demonstrate that general Bayesian methods can be used for line estimation. Bayesian methods, namely, given a model and noise, perform optimal inference over the data. Moreover, rather than only demonstrating the concept as such, the first results are promising with respect to the described clustering performance indicators. Further research is required to extend the method
to inference over multiple line segments and multiple volumetric objects that will need to be built on the mathematical foundation that has been laid down in this paper.@en