Point Cloud vs. Mesh Features for Building Interior Classification

Maarten Bassier,Florent Poux,Maarten Vergauwen

doi:10.3390/rs12142224

Maarten Bassier, Florent Poux + Show 1 more

Open Access

https://doi.org/10.3390/rs12142224

Copy DOI

Journal: Remote sensing	Publication Date: Jul 11, 2020
Citations: 22	License type: CC BY 4.0

Affiliation: KU Leuven, University of Liège

Abstract

Interpreting 3D point cloud data of the interior and exterior of buildings is essential for automated navigation, interaction and 3D reconstruction. However, the direct exploitation of the geometry is challenging due to inherent obstacles such as noise, occlusions, sparsity or variance in the density. Alternatively, 3D mesh geometries derived from point clouds benefit from preprocessing routines that can surmount these obstacles and potentially result in more refined geometry and topology descriptions. In this article, we provide a rigorous comparison of both geometries for scene interpretation. We present an empirical study on the suitability of both geometries for the feature extraction and classification. More specifically, we study the impact for the retrieval of structural building components in a realistic environment which is a major endeavor in Building Information Modeling (BIM) reconstruction. The study runs on segment-based structuration of both geometries and shows that both achieve recognition rates over 75% F1 score when suitable features are used.

Highlights

The automated interpretation of building environments is a major topic in the current literature [1]
We extend on the unsupervised segmentation frameworks proposed in [14,15] for both point cloud and 3D mesh geometries
Following the segment-based feature extraction presented in Section 3.2, our method proposes an empirical study to compare the achievable classification performance using shape, contextual and topology features from both the point cloud data and mesh data

Summary

Introduction

The automated interpretation of building environments is a major topic in the current literature [1]. The interpretation of building environments is typically performed on a set of observations such as imagery or point clouds From these inputs, a set of relevant features is extracted which is used to classify the observations [4]. The typical procedure to interpret building geometry is to first acquire a set of relevant observations, followed by one or more preprocessing steps to transform the raw data to a set of useful inputs i.e., mesh segments or voxel octrees. The geometry definitions, feature extraction and classification state of the art are discussed below Both point cloud data and meshes have different geometry representations depending on the type of data acquisition system and algorithm that is used to generate them. These approaches are bound to a specific sensor which limits the applicability

Methods

Results

Discussion

Conclusion