Unsupervised scene analysis and reconstruction using nonparametric Bayesian models

Robots operating in domestic environments need to deal with a variety of different objects. Often, these objects are neither placed randomly, nor independently of each other. For example, objects on a breakfast table such as plates, knives, or bowls typically occur in recurrent configurations. In this paper, we propose a novel hierarchical generative model to reason about latent object constellations in a scene. The proposed model is a combination of Dirichlet processes and beta processes, which allow for a probabilistic treatment of the unknown dimensionality of the parameter space. We show how the model can be employed to address a set of different tasks in scene understanding ranging from unsupervised scene segmentation to completion of a partially specified scene. We describe how sampling in this model can be done using Markov chain Monte Carlo (MCMC) techniques and present an experimental evaluation with simulated as well as real-world data obtained with a Kinect camera. I. INTRODUCTIONImagine a person laying a breakfast table and the person gets interrupted so that she cannot continue with the breakfast preparation. A service robot such as the one depicted in Fig. 1 should be able to proceed laying the table without receiving specific instructions. It faces a series of challenges: how to infer the total number of covers, how to infer which objects are missing on the table, and how should the missing parts be arranged. For this, the robot should not require any userspecific pre-programmed model but should ground its decision based on the breakfast tables it has seen in the past. In this paper, we address the problem of scene …