From a Point Cloud to a Simulation Model: Bayesian Segmentation and Entropy based Uncertainty Estimation for 3D Modelling

TL;DR

This paper presents a workflow for 3D indoor environment modeling from point clouds, utilizing Bayesian neural networks for segmentation and uncertainty estimation to improve model accuracy in factory simulations.

Contribution

It introduces a Bayesian segmentation approach for point clouds that enhances environment model accuracy through uncertainty-aware data processing.

Findings

Bayesian segmentation outperforms frequentist baseline.

Uncertainty information improves model placement accuracy.

Method validated on real-world and public datasets.

Abstract

The 3D modelling of indoor environments and the generation of process simulations play an important role in factory and assembly planning. In brownfield planning cases existing data are often outdated and incomplete especially for older plants, which were mostly planned in 2D. Thus, current environment models cannot be generated directly on the basis of existing data and a holistic approach on how to build such a factory model in a highly automated fashion is mostly non-existent. Major steps in generating an environment model in a production plant include data collection and pre-processing, object identification as well as pose estimation. In this work, we elaborate a methodical workflow, which starts with the digitalization of large-scale indoor environments and ends with the generation of a static environment or simulation model. The object identification step is realized using a Bayesian neural network capable of point cloud segmentation. We elaborate how the information on network uncertainty generated by a Bayesian segmentation framework can be used in order to build up a more accurate environment model. The steps of data collection and point cloud segmentation as well as the resulting model accuracy are evaluated on a real-world data set collected at the assembly line of a large-scale automotive production plant. The segmentation network is further evaluated on the publicly available Stanford Large-Scale 3D Indoor Spaces data set. The Bayesian segmentation network clearly surpasses the performance of the frequentist baseline and allows us to increase the accuracy of the model placement in a simulation scene considerably.