elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Fast and Accurate Large-scale Stereo Reconstruction using Variational Methods

Kuschk, Georg and Cremers, Daniel (2013) Fast and Accurate Large-scale Stereo Reconstruction using Variational Methods. In: Proceedings of ICCV2013, pp. 1-8. IEEE Xplore. ICCV Workshop on Big Data in 3D Computer Vision, 3.-6.12.2013, Sydney Conference Centre in Darling Harbour, Sydney.

Full text not available from this repository.

Official URL: http://www.iccv2013.org/index.php

Abstract

This paper presents a fast algorithm for high-accuracy large-scale outdoor dense stereo reconstruction of manmade environments. To this end, we propose a structureadaptive second-order Total Generalized Variation (TGV) regularization which facilitates the emergence of planar structures by enhancing the discontinuities along building facades. As data term we use cost functions which are robust to illumination changes arising in real world scenarios. Instead of solving the arising optimization problem by a coarse-to-fine approach, we propose a quadratic relaxation approach which is solved by an augmented Lagrangian method. This technique allows for capturing large displacements and fine structures simultaneously. Experiments show that the proposed augmented Lagrangian formulation leads to a speedup by about a factor of 2. The brightness-adaptive second-order regularization produces sub-disparity accurate and piecewise planar solutions, favoring not only fronto-parallel, but also slanted planes aligned with brightness edges in the resulting disparity maps. The algorithm is evaluated and shown to produce consistently good results for various data sets (close range indoor, ground based outdoor, aerial imagery).

Item URL in elib:https://elib.dlr.de/86185/
Document Type:Conference or Workshop Item (Speech)
Title:Fast and Accurate Large-scale Stereo Reconstruction using Variational Methods
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Kuschk, Georggeorg.kuschk (at) dlr.deUNSPECIFIED
Cremers, DanielTUMUNSPECIFIED
Date:2013
Journal or Publication Title:Proceedings of ICCV2013
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 1-8
Publisher:IEEE Xplore
Status:Published
Keywords:TGV
Event Title:ICCV Workshop on Big Data in 3D Computer Vision
Event Location:Sydney Conference Centre in Darling Harbour, Sydney
Event Type:international Conference
Event Dates:3.-6.12.2013
Organizer:ICCV Org.
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By:INVALID USER
Deposited On:19 Dec 2013 16:46
Last Modified:08 May 2014 23:30

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.