Print Email Facebook Twitter Classification of mobile laser scanning point clouds of urban scenes exploiting cylindrical neighbourhoods Title Classification of mobile laser scanning point clouds of urban scenes exploiting cylindrical neighbourhoods Author Zheng, M. (TU Delft OLD Department of GIS Technology; Wuhan University) Lemmens, M.J.P.M. (TU Delft OLD Department of GIS Technology) van Oosterom, P.J.M. (TU Delft OLD Department of GIS Technology) Date 2018 Abstract This paper presents our work on automated classification of Mobile Laser Scanning (MLS) point clouds of urban scenes with features derived from cylinders around points of consideration. The core of our method consists of spanning up a cylinder around points and deriving features, such as reflectance, height difference, from the points present within the cylindrical neighbourhood. Crucial in the approach is the selection of features from the points within the cylinder. An overall accuracy could be achieved, exploiting two bench mark data sets (Paris-rue-Madame and IQmulus & TerraMobilita) of 83% and 87% respectively. Subject 3D MappingClassificationCylindrical ApproachFeature extractionMobile laser scanningPoint clouds To reference this document use: http://resolver.tudelft.nl/uuid:af50be32-4d71-4550-8383-73fa9e5aea71 DOI https://doi.org/10.5194/isprs-archives-XLII-2-1225-2018 Publisher ISPRS Source International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42-2 Event ISPRS TC II Mid-term Symposium, 2018-06-04 → 2018-06-07, Riva del Garda, Italy Part of collection Institutional Repository Document type conference paper Rights © 2018 M. Zheng, M.J.P.M. Lemmens, P.J.M. van Oosterom Files PDF isprs_archives_XLII_2_1225_2018.pdf 1.08 MB Close viewer /islandora/object/uuid:af50be32-4d71-4550-8383-73fa9e5aea71/datastream/OBJ/view