Show simple item record

dc.contributor.author
Rosinol, Antoni
dc.contributor.supervisor
Sattler, Torsten
dc.contributor.supervisor
Pollefeys, Marc
dc.contributor.supervisor
Carlone, Luca
dc.date.accessioned
2018-11-30T07:08:00Z
dc.date.available
2018-10-20T20:16:23Z
dc.date.available
2018-10-31T07:05:26Z
dc.date.available
2018-11-08T07:08:10Z
dc.date.available
2018-11-30T07:08:00Z
dc.date.issued
2018-09-14
dc.identifier.uri
http://hdl.handle.net/20.500.11850/297645
dc.identifier.doi
10.3929/ethz-b-000297645
dc.description.abstract
The ideal vision system for an autonomous robot would not only provide the robot’s position and orientation (localization), but also an accurate and complete model of the scene (mapping). While localization information allows for controlling the robot, a map of the scene allows for collision-free navigation; combined, a robot can achieve full autonomy. Visual Inertial Odometry (VIO) algorithms have shown impressive localization results in recent years. Unfortunately, typical VIO algorithms use a point cloud to represent the scene, which is hardly usable for other tasks such as obstacle avoidance or path planning. In this work, we explore the possibility of generating a dense and consistent model of the scene by using a 3D mesh, while making use of structural regularities to improve both mesh and pose estimates. Our experimental results show that we can achieve a 26% more accurate pose estimates than state-of-the-art VIO algorithms when enforcing structural constraints, while also building a 3D mesh which provides a denser and more accurate map of the scene than a classical point cloud. We also show that our approach does not rely on assumptions about the scene and is general enough to work when structural regularities are not present. --> The ideal vision system for an autonomous robot would not only provide the robot’s position and orientation (localization), but also an accurate and complete model of the scene (mapping). While localization information allows for controlling the robot, a map of the scene allows for collision-free navigation; combined, a robot can achieve full autonomy. Visual Inertial Odometry (VIO) algorithms have shown impressive localization results in recent years. Unfortunately, typical VIO algorithms use a point cloud to represent the scene, which is hardly usable for other tasks such as obstacle avoidance or path planning. In this work, we explore the possibility of generating a dense and consistent model of the scene by using a 3D mesh, while making use of structural regularities to improve both mesh and pose estimates. Our experimental results show that we can achieve a 26\% more accurate pose estimates than state-of-the-art VIO algorithms when enforcing structural constraints, while also building a 3D mesh which provides a denser and more accurate map of the scene than a classical point cloud. We also show that our approach does not rely on assumptions about the scene and is general enough to work when structural regularities are not present.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
ETH Zurich; Massachusetts Institute of Technology (MIT)
en_US
dc.rights.uri
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject
Visual Inertial Odometry
en_US
dc.subject
Dense Mapping
en_US
dc.subject
State Estimation
en_US
dc.subject
SLAM
en_US
dc.subject
Robotics
en_US
dc.title
Densifying Sparse VIO: a Mesh-based approach using Structural Regularities
en_US
dc.title.alternative
{D}ensifying {S}parse {VIO}: a {M}esh-based approach using {S}tructural {R}egularities
en_US
dc.type
Master Thesis
dc.rights.license
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
dc.date.published
2018-10-31
ethz.size
176 p.
en_US
ethz.code.ddc
DDC - DDC::0 - Computer science, information & general works::004 - Data processing, computer science
en_US
ethz.code.jel
JEL - JEL::C - Mathematical and Quantitative Methods::C6 - Mathematical Methods; Programming Models; Mathematical and Simulation Modeling::C61 - Optimization Techniques; Programming Models; Dynamic Analysis
en_US
ethz.publication.place
Zurich; Cambridge, MA
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03766 - Pollefeys, Marc / Pollefeys, Marc
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03766 - Pollefeys, Marc / Pollefeys, Marc
en_US
ethz.tag
Master Thesis
en_US
ethz.date.deposited
2018-10-20T20:16:24Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2018-10-31T07:05:51Z
ethz.rosetta.lastUpdated
2021-02-15T02:52:12Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Densifying%20Sparse%20VIO:%20a%20Mesh-based%20approach%20using%20Structural%20Regularities&rft.date=2018-09-14&rft.au=Rosinol,%20Antoni&rft.genre=unknown&rft.btitle=Densifying%20Sparse%20VIO:%20a%20Mesh-based%20approach%20using%20Structural%20Regularities
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record