Dokumenttyp: Konferenzbeitrag
Titel: PCCT: A Point Cloud Classification Tool to Create 3D Training Data to Adjust and Develop 3D ConvNet
Autor*in: Barnefske, Eike Ruben 
Sternberg, Harald 
Quellenangabe: ISPRS ICWG II/III PIA19+MRSS19 - Photogrammetric Image Analysis & Munich Remote Sensing Symposium: Joint ISPRS conference
Erscheinungsdatum: 17-Sep-2019
Freie Schlagwörter: ConvNet; semantic labeling; training data; TLS; deep learning
Zusammenfassung: 
Point clouds give a very detailed and sometimes very accurate representation of the geometry of captured objects. In surveying, point clouds captured with laser scanners or camera systems are an intermediate result that must be processed further. Often the point cloud has to be divided into regions of similar types (object classes) for the next process steps. These classifications are very time-consuming and cost-intensive compared to acquisition. In order to automate this process step, conventional neural networks (ConvNet), which take over the classification task, are investigated in detail. In addition to the network architecture, the classification performance of a ConvNet depends on the training data with which the task is learned. This paper presents and evaluates the point clould classification tool (PCCT) developed at HCU Hamburg. With the PCCT, large point cloud collections can be semi-automatically classified. Furthermore, the influence of erroneous points in three-dimensional point clouds is investigated. The network architecture PointNet is used for this investigation.
Sachgruppe (DDC): 620: Ingenieurwissenschaften
HCU-Fachgebiet / Studiengang: Hydrographie und Geodäsie 
Seite von: 35
Seite bis: 40
Verlag: Copernicus
Teil der Schriftenreihe: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 
Bandangabe: XLII-2/W16
Verlagslink (DOI): 10.5194/isprs-archives-XLII-2-W16-35-2019
URN (Zitierlink): urn:nbn:de:gbv:1373-repos-10127
Direktlink: https://repos.hcu-hamburg.de/handle/hcu/793
Sprache: Englisch
Creative-Commons-Lizenz: https://creativecommons.org/licenses/by/4.0/
Enthalten in der SammlungPublikationen (mit Volltext)

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat
isprs-archives-XLII-2-W16-35-2019.pdf1.22 MBAdobe PDFÖffnen/Anzeigen
Internformat

Seitenansichten

327
checked on 24.12.2024

Download(s)

60
checked on 24.12.2024

Google ScholarTM

Prüfe

Export

Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons