Point-level Uncertainty Evaluation of Mobile Laser Scanning Point Clouds

TL;DR

This paper introduces a machine learning framework using ensemble models to evaluate point-level uncertainty in mobile laser scanning point clouds, enabling scalable and accurate uncertainty quantification without relying on costly reference data.

Contribution

It presents a novel data-driven approach employing Random Forest and XGBoost models to predict uncertainty based on geometric features, avoiding the need for high-precision reference data.

Findings

Models achieved ROC-AUC above 0.87 in predicting uncertainty.

Geometric features like elevation variation and point density are key predictors.

Framework is scalable and adaptable for large-scale point cloud quality control.

Abstract

Reliable quantification of uncertainty in Mobile Laser Scanning (MLS) point clouds is essential for ensuring the accuracy and credibility of downstream applications such as 3D mapping, modeling, and change analysis. Traditional backward uncertainty modeling heavily rely on high-precision reference data, which are often costly or infeasible to obtain at large scales. To address this issue, this study proposes a machine learning-based framework for point-level uncertainty evaluation that learns the relationship between local geometric features and point-level errors. The framework is implemented using two ensemble learning models, Random Forest (RF) and XGBoost, which are trained and validated on a spatially partitioned real-world dataset to avoid data leakage. Experimental results demonstrate that both models can effectively capture the nonlinear relationships between geometric characteristics and uncertainty, achieving mean ROC-AUC values above 0.87. The analysis further reveals that geometric features describing elevation variation, point density, and local structural complexity play a dominant role in predicting uncertainty. The proposed framework offers a data-driven perspective of uncertainty evaluation, providing a scalable and adaptable foundation for future quality control and error analysis of large-scale point clouds.