Publikation:

Lidar assisted Depth Estimation for Thermal Cameras

Lade...
Vorschaubild

Dateien

Jandeleit_2-vdtn88xxgotj1.pdf
Jandeleit_2-vdtn88xxgotj1.pdfGröße: 6.8 MBDownloads: 202

Datum

2022

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

DOI (zitierfähiger Link)
ArXiv-ID

Internationale Patentnummer

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Bachelorarbeit
Publikationsstatus
Published

Erschienen in

Zusammenfassung

Depth- and pose estimation are classical problems in computer vision. Estimating the depth of thermal cameras can be achieved by estimating the camera poses in an independently captured lidar scan. In underground environments and animal behavior, thermal cameras are often used instead of classical RGB cameras. But existing methods for RGB pose estimation do not necessarily need to be effective for thermal cameras, because their working mode and data are different. This is the case for subterranean cave environments. Thermal cameras can be used to capture animal behavior in dark caves. This is what this paper is focused on. This work provides a systematic approach to the alignment of lidar and thermal image information. We use the Ushichka dataset as an exemplary study case. Classical computer vision techniques like Direct Linear Triangulation and Space Carving are are applied to the dataset. We find that the classical methods do not work here as expected and provide a semi-automatic framework, called DMCP, to solve the registration. Finally, different approaches are compared in order to point out in which way a fully automatic registration might be possible.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Pose Estimation, Camera-LiDAR, Sensor Fusion.

Konferenz

Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690JANDELEIT, Julian, 2022. Lidar assisted Depth Estimation for Thermal Cameras [Bachelorarbeit]. Konstanz: Universität Konstanz
BibTex
@mastersthesis{Jandeleit2022Lidar-57714,
  year={2022},
  title={Lidar assisted Depth Estimation for Thermal Cameras},
  address={Konstanz},
  school={Universität Konstanz},
  author={Jandeleit, Julian}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/57714">
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57714"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-06-01T08:23:09Z</dc:date>
    <dcterms:issued>2022</dcterms:issued>
    <dc:creator>Jandeleit, Julian</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57714/3/Jandeleit_2-vdtn88xxgotj1.pdf"/>
    <dc:language>eng</dc:language>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57714/3/Jandeleit_2-vdtn88xxgotj1.pdf"/>
    <dc:contributor>Jandeleit, Julian</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:abstract xml:lang="eng">Depth- and pose estimation are classical problems in computer vision. Estimating the depth of thermal cameras can be achieved by estimating the camera poses in an independently captured lidar scan. In underground environments and animal behavior, thermal cameras are often used instead of classical RGB cameras. But existing methods for RGB pose estimation do not necessarily need to be effective for thermal cameras, because their working mode and data are different. This is the case for subterranean cave environments. Thermal cameras can be used to capture animal behavior in dark caves. This is what this paper is focused on. This work provides a systematic approach to the alignment of lidar and thermal image information. We use the Ushichka dataset as an exemplary study case. Classical computer vision techniques like Direct Linear Triangulation and Space Carving are are applied to the dataset. We find that the classical methods do not work here as expected and provide a semi-automatic framework, called DMCP, to solve the registration. Finally, different approaches are compared in order to point out in which way a fully automatic registration might be possible.</dcterms:abstract>
    <dcterms:title>Lidar assisted Depth Estimation for Thermal Cameras</dcterms:title>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-06-01T08:23:09Z</dcterms:available>
  </rdf:Description>
</rdf:RDF>

Interner Vermerk

xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter

Kontakt
URL der Originalveröffentl.

Prüfdatum der URL

Prüfungsdatum der Dissertation

Hochschulschriftenvermerk
Konstanz, Universität Konstanz, Bachelorarbeit, 2022
Finanzierungsart

Kommentar zur Publikation

Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
Begutachtet
Diese Publikation teilen