Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Kumar, Ashutosh [VerfasserIn]   i
 Anders, Katharina [VerfasserIn]   i
 Winiwarter, Lukas [VerfasserIn]   i
 Höfle, Bernhard [VerfasserIn]   i
Titel:Feature relevance analysis for 3D point cloud classification using deep learning
Verf.angabe:Ashutosh Kumar, Katharina Anders, Lukas Winiwarter, Bernhard Höfle
E-Jahr:2019
Jahr:29 May 2019
Umfang:8 S.
Fussnoten:Gesehen am 17.06.2024
Titel Quelle:Enthalten in: ISPRS Geospatial Week (4. : 2019 : Enschede)ISPRS Geospatial Week 2019
Ort Quelle:[Göttingen] : [Copernicus Publications], 2019
Jahr Quelle:2019
Band/Heft Quelle:(2019), Seite 317-324
Abstract:3D point clouds acquired by laser scanning and other techniques are difficult to interpret because of their irregular structure. To make sense of this data and to allow for the derivation of useful information, a segmentation of the points in groups, units, or classes fit for the specific use case is required. In this paper, we present a non-end-to-end deep learning classifier for 3D point clouds using multiple sets of input features and compare it with an implementation of the state-of-the-art deep learning framework PointNet++. We first start by extracting features derived from the local normal vector (normal vectors, eigenvalues, and eigenvectors) from the point cloud, and study the result of classification for different local search radii. We extract additional features related to spatial point distribution and use them together with the normal vector-based features. We find that the classification accuracy improves by up to 33% as we include normal vector features with multiple search radii and features related to spatial point distribution. Our method achieves a mean Intersection over Union (mIoU) of 94% outperforming PointNet++’s Multi Scale Grouping by up to 12%. The study presents the importance of multiple search radii for different point cloud features for classification in an urban 3D point cloud scene acquired by terrestrial laser scanning.
DOI:doi:10.5194/isprs-annals-IV-2-W5-373-2019
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

kostenfrei: Volltext: https://doi.org/10.5194/isprs-annals-IV-2-W5-373-2019
 kostenfrei: Volltext: https://isprs-annals.copernicus.org/articles/IV-2-W5/373/2019/4950
 DOI: https://doi.org/10.5194/isprs-annals-IV-2-W5-373-2019
Datenträger:Online-Ressource
Sprache:eng
K10plus-PPN:1891393367
Verknüpfungen:→ Sammelwerk

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69223832   QR-Code
zum Seitenanfang