- AutorIn
- Reuma Arav Dept. of Geodesy and Geoinformation, TU Wien, Austria
- Dennis WittichInstitute of Photogrammetry and GeoInformation, Leibniz University Hannover, Germany
- Franz RottensteinerInstitute of Photogrammetry and GeoInformation, Leibniz University Hannover, Germany
- Titel
- Deep learning of topographic anomalies for the detection of regions of interest in 3D point clouds
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-985351
- Konferenz
- 5th Virtual Geoscience Conference. Dresden, 21. - 22. September 2023
- Quellenangabe
- VGC 2023 - Unveiling the dynamic Earth with digital methods
Herausgeber: Helmholtz-Institut Freiberg für Ressourcentechnologie
Herausgeber: Technische Universität Dresden
Erscheinungsort: Dresden
Erscheinungsjahr: 2023
Seiten: 44-45 - Erstveröffentlichung
- 2023
- DOI
- https://doi.org/10.25368/2025.175
- Abstract (EN)
- Three-dimensional point clouds are ubiquitous in the study of natural environments. These point clouds hold extensive datasets that pose challenges for analysis. This is particularly because the collected data contains a diverse set of objects, at varying shapes and sizes, that are distributed throughout the data, and intricately intertwined within the topography. In such cases, it is difficult to focus on the important regions and perform the required analyses.
- Freie Schlagwörter (DE)
- Geowissenschaften, Geomatik, Photogrammetrie, Umweltüberwachung
- Freie Schlagwörter (EN)
- visual saliency, geomorphological entities, natural environment, lidar, photogrammetry, deep neu-ral network.
- Klassifikation (DDC)
- 550
- Klassifikation (RVK)
- RB 10081
- Herausgeber (Institution)
- Helmholtz-Institut Freiberg für Ressourcentechnologie, Freiberg
- Technische Universität Dresden, Dresden
- Förder- / Projektangaben
- European Commission (EC)
H2020 | MSCA-IF-EF-ST
Morphological Entities detection and characterisation from 3-D laser scanned point-clouds
(MorE3D)
ID: 896409 - Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-985351
- Veröffentlichungsdatum Qucosa
- 18.08.2025
- Dokumenttyp
- Konferenzbeitrag
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0