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

Stereo Depth Estimation using Deep Learning: Leveraging Context through Multi-Task Training

True, Steffen (2018) Stereo Depth Estimation using Deep Learning: Leveraging Context through Multi-Task Training. DLR-Interner Bericht. DLR-IB-RM-OP-2018-230. Master's. Technical University of Munich. 82 S. (Unpublished)

[img] PDF - Only accessible within DLR


Dense depth information is vital for robotics applications to fully understand or reconstruct a 3D scene. Recent work has shown that stereo depth estimation through binocular disparity has been successfully cast a learning problem lever- aging convolutional neural networks for a constant surge in performance and accuracy. However, textureless regions, object boundaries and small details still give rise to challenges. The explicit incorporation of semantic knowledge can po- tentially mitigate this problem by providing high-level information specifically for objects and smooth regions. The proposed network architecture derives a com- mon representation for semantic segmentation and disparity estimation through multi-task learning, where the use of an auxiliary task has proven beneficial in terms of learning efficiency and prediction accuracy of the assigned tasks. The training of the disparity estimation model was enabled by synthetically generated data, whereas the resulting disparity output is tested on real images and com- pared in multiple scenarios to a state-of-the-art traditional algorithm.

Item URL in elib:https://elib.dlr.de/125041/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Stereo Depth Estimation using Deep Learning: Leveraging Context through Multi-Task Training
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
True, SteffenSteffen.True (at) dlr.deUNSPECIFIED
Date:12 December 2018
Refereed publication:No
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Number of Pages:82
Keywords:Stereo, Depth, Disparity, Segmentation, Multi-task, Deep Learning, CNN
Institution:Technical University of Munich
Department:Department of Informatics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: True, Steffen
Deposited On:14 Dec 2018 00:24
Last Modified:14 Dec 2018 00:24

Repository Staff Only: item control page

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