Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Feature evaluation for building facade images - an empirical study

Title: Feature evaluation for building facade images - an empirical study
Authors: Yang, Michael Ying; Foerstner, Wolfgang; Chai, Dengfeng; Shortis, M.; Paparoditis, N.; Mallet, C.
Source: XXII ISPRS Congress, Technical Commission III ; The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; 39-B3
Publisher Information: Copernicus Publications
Publication Year: 2012
Collection: Institutional Repository of Leibniz Universität Hannover
Subject Terms: Feature; evaluation; random decision forest; facade image; randomized trees; segmentation; recognition; ddc:550; Konferenzschrift
Description: The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.
Document Type: book part
Language: English
ISSN: 1682-1750
Relation: ESSN:2194-9034; http://dx.doi.org/10.15488/1096
DOI: 10.15488/1096
Availability: http://www.repo.uni-hannover.de/handle/123456789/1120; https://doi.org/10.15488/1096
Rights: CC BY 3.0 Unported ; https://creativecommons.org/licenses/by/3.0/ ; frei zugänglich
Accession Number: edsbas.8666B4E1
Database: BASE