Gaussian Process Mapping of Uncertain Building Models with GMM as Prior

TL;DR

This paper introduces a probabilistic mapping method using Gaussian Processes and GMMs to model uncertain building surfaces, improving map accuracy and uncertainty quantification in urban LiDAR data.

Contribution

It proposes a novel combination of GMM-extracted facets with implicit GP maps to efficiently model building surface uncertainty, outperforming existing methods.

Findings

Higher Precision-Recall AUC compared to other mapping methods

Effective uncertainty quantification for building models

Reduced computation for simple planar objects

Abstract

Mapping with uncertainty representation is required in many research domains, especially for localization. Although there are many investigations regarding the uncertainty of the pose estimation of an ego-robot with map information, the quality of the reference maps is often neglected. To avoid potential problems caused by the errors of maps and a lack of uncertainty quantification, an adequate uncertainty measure for the maps is required. In this letter, uncertain building models with abstract map surfaces using Gaussian Processes (GPs) are proposed to describe the map uncertainty in a probabilistic way. To reduce the redundant computation for simple planar objects, extracted facets from a Gaussian Mixture Model (GMM) are combined with an implicit GP map, also employing local GP-block techniques. The proposed method is evaluated on LiDAR point clouds of city buildings collected by a mobile mapping system. Compared to the performance of other methods such as OctoMap, GP Occupancy Map (GPOM), Bayesian Generalized Kernel OctoMap (BGKOctoMap), Local automatic relevance determination Hilbert map (LARD-HM) and Gaussian Implicit Surface map (GPIS), our method achieves a higher Precision-Recall AUC for the evaluated buildings.