Centre de documentation
scientifique

Dépouillements

Effiziente Interpretation von 3D-Punktwolken durch die Abschätzung der Relevanz von Merkmalen / Martin Weinmann in AVN Allgemeine Vermessungs-Nachrichten, vol 2015 n° 10 (Oktober 2015)    

Public [article]  inAVN Allgemeine Vermessungs-Nachrichten > vol 2015 n° 10 (Oktober 2015) . - pp 308 - 315 Titre : Effiziente Interpretation von 3D-Punktwolken durch die Abschätzung der Relevanz von Merkmalen Titre original : Efficient interpretation of 3D point clouds by assessing feature relevance Type de document : Article/Communication Auteurs : Martin Weinmann, Auteur ; Clément Mallet , Auteur ; Stefan Hinz, Auteur ; Boris Jutzi, Auteur Année de publication : 2015 Article en page(s) : pp 308 - 315 Langues : Allemand (ger) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] évaluation [Termes IGN] interprétation automatique [Termes IGN] semis de points Résumé : (auteur) The automatic analysis of large 3D point clouds represents a crucial task in photogrammetry, remote sensing and computer vision. In this paper, we propose a new methodology for the semantic interpretation of such point clouds which involves feature relevance assessment in order to reduce both processing time and memory consumption. Given a standard benchmark dataset with 1.3 million 3D points, we first extract a set of 21 geometric 3D and 2D features. Subsequently, we apply a classifier-independent ranking procedure which involves a general relevance metric in order to derive compact and robust subsets of versatile features which are generally applicable for a large variety of subsequent tasks. This metric is based on 7 different feature selection strategies and thus addresses different intrinsic properties of the given data. For the example of semantically interpreting 3D point cloud data, we demonstrate the great potential of smaller subsets consisting of only the most relevant features with 4 different state-of-the-art classifiers. The results reveal that, instead of including as many features as possible in order to compensate for lack of knowledge, a crucial task such as scene interpretation can be carried out with only few versatile features and even improved accuracy. Numéro de notice : A2015--062 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueNat DOI : sans En ligne : https://gispoint.de/index.php?eID=dumpFile&t=f&f=13316&token=a8c29ff23fbe27ec87e [...] Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83509 [article]

Documents numériques

en open access Effiziente Interpretation ... - pdf éditeur Adobe Acrobat PDF