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

Using Self-Contradiction to Learn Confidence Measures in Stereo Vision

Mostegel, Christian and Rumpler, Markus and Fraundorfer, Friedrich and Bischof, Horst (2016) Using Self-Contradiction to Learn Confidence Measures in Stereo Vision. In: Proceedings of Computer Vision and Pattern Recognition 2016, pp. 4067-4076. IEEE Xplore. Conference on Computer Vision and Pattern Recognition 2016, 27-30 June 2016, Las Vegas, USA.

[img] PDF
2MB

Official URL: http://cvpr2016.thecvf.com/program/news_updates#proceedings

Abstract

Learned confidence measures gain increasing impor- tance for outlier removal and quality improvement in stereo vision. However, acquiring the necessary training data is typically a tedious and time consuming task that involves manual interaction, active sensing devices and/or synthetic scenes. To overcome this problem, we propose a new, flexi- ble, and scalable way for generating training data that only requires a set of stereo images as input. The key idea of our approach is to use different view points for reason- ing about contradictions and consistencies between multi- ple depth maps generated with the same stereo algorithm. This enables us to generate a huge amount of training data in a fully automated manner. Among other experiments, we demonstrate the potential of our approach by boost- ing the performance of three learned confidence measures on the KITTI2012 dataset by simply training them on a vast amount of automatically generated training data rather than a limited amount of laser ground truth data.

Item URL in elib:https://elib.dlr.de/105149/
Document Type:Conference or Workshop Item (Poster)
Title:Using Self-Contradiction to Learn Confidence Measures in Stereo Vision
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Mostegel, Christianmostegel (at) icg.tugraz.atUNSPECIFIED
Rumpler, Markusrumpler (at) icg.tugraz.atUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.deUNSPECIFIED
Bischof, Horstbischof (at) icg.tu-graz.ac.atUNSPECIFIED
Date:2016
Journal or Publication Title:Proceedings of Computer Vision and Pattern Recognition 2016
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 4067-4076
Publisher:IEEE Xplore
Status:Published
Keywords:Confidence Measures, Stereo Vision
Event Title:Conference on Computer Vision and Pattern Recognition 2016
Event Location:Las Vegas, USA
Event Type:international Conference
Event Dates:27-30 June 2016
Organizer:IEEE Computer Society and the Computer Vision Foundation (CVF)
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - Vabene++ (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By:INVALID USER
Deposited On:20 Jul 2016 10:35
Last Modified:31 Jul 2019 20:02

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.