Title: Multi-view random fields and street-side imagery
Authors: Recky, Michal
Leberl, Franz
Ferko, Andrej
Citation: Journal of WSCG. 2012, vol. 20, no. 2, p. 137-144.
Issue Date: 2012
Publisher: Václav Skala - UNION Agency
Document type: článek
URI: http://wscg.zcu.cz/WSCG2012/!_2012-Journal-Full-2.pdf
ISSN: 1213–6972 (hardcopy)
1213–6980 (CD-ROM)
1213–6964 (on-line)
Keywords: náhodná pole;grafické modely;multi-view scénáře;počítačové vidění
Keywords in different language: random fields;graphic models;multi-view scenarios;computer vision
Abstract: In this paper, we present a method that introduces graphical models into a multi-view scenario. We focus on a popular Random Fields concept that many researchers use to describe context in a single image and introduce a new model that can transfer context directly between matched images – Multi-View Random Fields. This method allows sharing not only visual information between images, but also contextual information for the purpose of object recognition and classification. We describe the mathematical model for this method as well as present the application for a domain of street-side image datasets. In this application, the detection of façade elements has improved by up to 20% using Multi-view Random Fields.
Rights: © Václav Skala - UNION Agency
Appears in Collections:Number 2 (2012)

Files in This Item:
File Description SizeFormat 
Recky.pdf490,52 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/1074

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.