Accuracy Assessment of Cultural Heritage Models Extracting 3D Point Cloud Geometric Features with RPAS SfM-MVS and TLS Techniques

Alessandra Capolupo

doi:10.3390/drones5040145

Abstract

A proper classification of 3D point clouds allows fully exploiting data potentiality in assessing and preserving cultural heritage. Point cloud classification workflow is commonly based on the selection and extraction of respective geometric features. Although several research activities have investigated the impact of geometric features on classification outcomes accuracy, only a few works focused on their accuracy and reliability. This paper investigates the accuracy of 3D point cloud geometric features through a statistical analysis based on their corresponding eigenvalues and covariance with the aim of exploiting their effectiveness for cultural heritage classification. The proposed approach was separately applied on two high-quality 3D point clouds of the All Saints’ Monastery of Cuti (Bari, Southern Italy), generated using two competing survey techniques: Remotely Piloted Aircraft System (RPAS) Structure from Motion (SfM) and Multi View Stereo (MVS) techniques and Terrestrial Laser Scanner (TLS). Point cloud compatibility was guaranteed through re-alignment and co-registration of data. The geometric features accuracy obtained by adopting the RPAS digital photogrammetric and TLS models was consequently analyzed and presented. Lastly, a discussion on convergences and divergences of these results is also provided.

Highlights

Monitoring a cultural heritage building is essential to evaluate its health status and detect any deformations that have occurred as well as to preserve and disseminate its relevance
The geometric features accuracy obtained by adopting the Remotely Piloted Aircraft System (RPAS) digital photogrammetric and Terrestrial Laser Scanner (TLS) models was analyzed and presented
3D models are currently recognized as a powerful tool to document the current state of a cultural building [2]

Summary

Introduction

Monitoring a cultural heritage building is essential to evaluate its health status and detect any deformations that have occurred as well as to preserve and disseminate its relevance. Such purposes can be achieved by producing an accurate three-dimensional (3D). The 3D models, can capture their appearances and reproduce their geometric details digitally [1]. 3D models are currently recognized as a powerful tool to document the current state of a cultural building [2]. Over the years several methodologies have been proposed to generate accurate and reliable 3D digital scene reconstruction. Image-based modeling (e.g., photogrammetry), the range-based approach (e.g., Terrestrial Laser Scanner), or the integration of the abovementioned technologies are currently recognized as the most productive [2]

Objectives

Methods

Results

Conclusion