A Bayesian framework for 3D point cloud filtering

Abstract

This paper introduces a novel Bayesian filtering technique for the filtration of ground points in complex terrain and steep inclines in remote sensing applications. The technique integrates LAStools and statistical techniques, generating a posterior distribution using prior probability and likelihood functions. It is applied to point cloud data from UAV aerial images and DSM formats. The study shows that the Bayesian method improves the outcome in sloping regions compared to other algorithms like LAStools, Statistical, and CSF. In flat terrain, the CSF approach produced the highest F1 score, while the Bayesian method showed degradation but outperformed statistical and LAStools approaches.