KIT | KIT-Bibliothek | Impressum | Datenschutz

3D Indoor Mapping with the Microsoft HoloLens: Qualitative and Quantitative Evaluation by Means of Geometric Features

Weinmann, Martin; Jäger, Miriam Amelie; Wursthorn, Sven; Jutzi, Boris ORCID iD icon; Weinmann, Michael; Hübner, Patrick

Abstract (englisch):

3D indoor mapping and scene understanding have seen tremendous progress in recent years due to the rapid development of sensorsystems, reconstruction techniques and semantic segmentation approaches. However, the quality of the acquired data stronglyinfluences the accuracy of both reconstruction and segmentation. In this paper, we direct our attention to the evaluation of themapping capabilities of the Microsoft HoloLens in comparison to high-quality TLS systems with respect to 3D indoor mapping,feature extraction and semantic segmentation. We demonstrate how a set of rather interpretable low-level geometric features andthe resulting semantic segmentation achieved with a Random Forest classifier applied on these features are affected by the qualityof the acquired data. The achieved results indicate that, while allowing for a fast acquisition of room geometries, the HoloLensprovides data with sufficient accuracy for a wide range of applications.

Verlagsausgabe §
DOI: 10.5445/IR/1000123250
Veröffentlicht am 28.11.2021
DOI: 10.5194/isprs-annals-V-1-2020-165-2020
Zitationen: 18
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
KIT-Zentrum Klima und Umwelt (ZKU)
Publikationstyp Zeitschriftenaufsatz
Publikationsdatum 03.08.2020
Sprache Englisch
Identifikator ISSN: 2194-9050
KITopen-ID: 1000123250
Erschienen in ISPRS annals
Verlag Copernicus Publications
Band V-1-2020
Seiten 165–172
Bemerkung zur Veröffentlichung 2020 XXIV ISPRS Congress
Schlagwörter 3D, Indoor Mapping, HoloLens, Feature Extraction, Classification, Semantic Segmentation, Evaluation
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page