Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Manhattan scene understanding using monocular, stereo, and 3D features
Author: Flint, A.
Murray, D.
Reid, I.
Citation: 2011 IEEE International Conference on Computer Vision, 2011 / pp.2228-2235
Publisher: IEEE
Publisher Place: USA
Issue Date: 2011
Series/Report no.: IEEE International Conference on Computer Vision
ISBN: 9781457711015
ISSN: 1550-5499
Conference Name: 2011 IEEE International Conference on Computer Vision (ICCV) (06 Nov 2011 - 13 Nov 2011 : Barcelona, Spain)
Statement of
Alex Flint, David Murray, and Ian Reid
Abstract: This paper addresses scene understanding in the context of a moving camera, integrating semantic reasoning ideas from monocular vision with 3D information available through structure-from-motion. We combine geometric and photometric cues in a Bayesian framework, building on recent successes leveraging the indoor Manhattan assumption in monocular vision. We focus on indoor environments and show how to extract key boundaries while ignoring clutter and decorations. To achieve this we present a graphical model that relates photometric cues learned from labeled data, stereo photo-consistency across multiple views, and depth cues derived from structure-from-motion point clouds. We show how to solve MAP inference using dynamic programming, allowing exact, global inference in ~100 ms (in addition to feature computation of under one second) without using specialized hardware. Experiments show our system out-performing the state-of-the-art.
Rights: ©2011 IEEE
RMID: 0020131163
DOI: 10.1109/ICCV.2011.6126501
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_88230.pdfRestricted Access1.5 MBAdobe PDFView/Open

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