Tentative Tests on Two Rapid Multispectral Classifiers for Classifying Point Clouds
Mingxue Zheng (TU Delft - OLD Department of GIS Technology, Wuhan University)
Mathias Lemmens (TU Delft - OLD Department of GIS Technology)
P.J.M. van Oosterom (TU Delft - OLD Department of GIS Technology)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
This paper focusses on the feasibility of classifiers, developed for classifying multispectral images, for assigning classes to point clouds of urban scenes. The motivation of our research is that dense point clouds require fast classification methods to extract meaningful information within a reasonable amount of time and multispectral classifiers do have this property. We employ two encoding methods acting on one feature: the altitude above street level. We emphasize computation time and therefore we use just one feature in this prelimina