Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/5232
Title: Joint optimization for object class segmentation and dense stereo reconstruction
Authors: Ladicky, Lubor
Sturgess, Paul
Russell, Chris
Sengupta, Sunando
Baştanlar, Yalın
Clocksin, William
Torr, Philip H.S.
Baştanlar, Yalın
Izmir Institute of Technology. Computer Engineering
Keywords: Dense stereo reconstruction
Random fields
Object class segmentation
Image segmentation
Optimization
Issue Date: Nov-2012
Publisher: Springer Verlag
Source: Ladicky, L., Sturgess, P., Russell, C., Sengupta, S., Baştanlar, Y., Clocksin, W., and Torr, P.H.S. (2012). Joint optimization for object class segmentation and dense stereo reconstruction. International Journal of Computer Vision, 100(2), 122-133. doi:10.1007/s11263-011-0489-0
Abstract: The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leu-ven data set (http://cms.brookes.ac.uk/research/visiongroup/ files/Leuven.zip), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (http://cms.brookes.ac.uk/ staff/Philip-Torr/ale.htm). © 2011 Springer Science+Business Media, LLC.
URI: http://doi.org/10.1007/s11263-011-0489-0
http://hdl.handle.net/11147/5232
ISSN: 0920-5691
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
5232.pdfMakale2.76 MBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

SCOPUSTM   
Citations

76
checked on Sep 18, 2021

WEB OF SCIENCETM
Citations

60
checked on Sep 18, 2021

Page view(s)

44
checked on Sep 21, 2021

Download(s)

28
checked on Sep 21, 2021

Google ScholarTM

Check

Altmetric


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