Show simple item record

dc.contributor.author
Digumarti, Sundara Tejaswi
dc.contributor.supervisor
Siegwart, Roland
dc.contributor.supervisor
Beardsley, Paul
dc.contributor.supervisor
Deussen, Oliver
dc.date.accessioned
2020-01-22T06:55:58Z
dc.date.available
2020-01-21T23:04:54Z
dc.date.available
2020-01-22T06:54:13Z
dc.date.available
2020-01-22T06:55:58Z
dc.date.issued
2019-12-03
dc.identifier.uri
http://hdl.handle.net/20.500.11850/392796
dc.identifier.doi
10.3929/ethz-b-000392796
dc.description.abstract
Research on reconstruction of objects and environments in three dimensions has made great progress over the past decade. Applications such as building maps of environments, creating 3D models for robot manipulation, and generating digital content for use in movies, games and virtual environments all benefit from techniques that can reconstruct objects with high fidelity and accuracy. Robustness of the reconstruction pipeline can be improved by incorporating semantic information from the environment. Semantic information also supplements the reconstructed model enabling applications such as robot manipulation, measurement of class specific metrics, and artistic control of objects. However, a vast majority of this research, both reconstruction and semantic segmentation, is targeted towards human-made objects and environments. These are characterized by geometry that is easier to parametrize, and features such as corners and edges, that can be tracked reliably even from viewpoints that are far apart. On the other hand, natural structures such as trees, foliage and corals consist of elements that are self-similar, repetitive, non-parametric and semi-rigid, have self-occluding geometry and display limited variation in colour information. This renders it challenging to apply the techniques developed for human made objects in natural environments. The focus of this thesis is to develop algorithms to tackle some of these challenges and enable high quality reconstruction of natural structures. Understanding semantics helps mitigate some of these challenges. To this end we propose three algorithms for semantic segmentation of vegetation. The first algorithm proposes the use of features based on surface curvatures as the representation of local geometry. The second one aims to learn these features using a Convolutional Neural Network (CNN). The third method also uses CNNs but performs semantic segmentation in single frame RGB-D images, as opposed to full point clouds used in the first two approaches. As this approach learns features from partial observations of geometry, it can be used in improving the robustness of the reconstruction framework. Due to complexity in deriving accurate parametric models of the unstructured geometry, we take a data-driven approach in all the three algorithms and learn features directly from the data. Data required for this purpose is generated using state-of-the-art simulation software. Evaluation on real data shows the extent to which knowledge transfers from simulation to reality. Improving camera tracking paves way for better reconstruction accuracy. Given that traditional feature based approaches perform poorly in natural environments, we employ deep neural networks to learn robust features directly from the environment. Here, we push the data-driven approach to its limit and investigate if a deep neural network can learn to predict poses from input images through end-to-end learning. Finally, we extend the scope of the aforementioned techniques for underwater environments to facilitate scanning and reconstruction of coral reefs. We demonstrate underwater 3D capture using commodity depth cameras and present an algorithm to calibrate a camera and its housing in order to undo the distortions caused due to refraction.
en_US
dc.format
application/zip
en_US
dc.language.iso
en
en_US
dc.publisher
ETH Zurich
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Semantic segmentation
en_US
dc.subject
Mapping
en_US
dc.subject
Deep Learning
en_US
dc.subject
Vegetation modeling
en_US
dc.subject
3D Reconstruction
en_US
dc.title
Semantic Segmentation and Mapping for Natural Environments
en_US
dc.type
Doctoral Thesis
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2020-01-22
ethz.size
127 p.
en_US
ethz.code.ddc
DDC - DDC::6 - Technology, medicine and applied sciences::620 - Engineering & allied operations
en_US
ethz.code.ddc
DDC - DDC::6 - Technology, medicine and applied sciences::600 - Technology (applied sciences)
en_US
ethz.notes
This thesis was a joint collaboration with ETH Zurich and Disney Research.
en_US
ethz.identifier.diss
26285
en_US
ethz.publication.place
Zurich
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02620 - Inst. f. Robotik u. Intelligente Systeme / Inst. Robotics and Intelligent Systems::03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
en_US
ethz.relation.hasPart
20.500.11850/318584
ethz.relation.hasPart
20.500.11850/384158
ethz.relation.hasPart
20.500.11850/118394
ethz.date.deposited
2020-01-21T23:05:02Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.identifier.internal
Doctoral Thesis - Sundara Tejaswi Digumarti
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2020-01-22T06:54:28Z
ethz.rosetta.lastUpdated
2020-02-15T23:45:06Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Semantic%20Segmentation%20and%20Mapping%20for%20Natural%20Environments&rft.date=2019-12-03&rft.au=Digumarti,%20Sundara%20Tejaswi&rft.genre=unknown&rft.btitle=Semantic%20Segmentation%20and%20Mapping%20for%20Natural%20Environments
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record