Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
http://dx.doi.org/10.18419/opus-10674
Langanzeige der Metadaten
DC Element | Wert | Sprache |
---|---|---|
dc.contributor.author | Stumber, Jonathan | - |
dc.date.accessioned | 2020-01-08T10:50:01Z | - |
dc.date.available | 2020-01-08T10:50:01Z | - |
dc.date.issued | 2019 | de |
dc.identifier.other | 1689451688 | - |
dc.identifier.uri | http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-106919 | de |
dc.identifier.uri | http://elib.uni-stuttgart.de/handle/11682/10691 | - |
dc.identifier.uri | http://dx.doi.org/10.18419/opus-10674 | - |
dc.description.abstract | In the last years, convolutional neural network (CNN) based methods are becoming more and more popular to estimate optical flow. Recently, state-of-the art optical flow methods often use multiple frames to make use of temporal information. However, a prediction based on previous frames was not studied separately from the flow estimation for CNN based learning approaches. In this thesis various network structures are tested, compared and improved for this task. The best results were obtained by using warped backward and forward flows from two previous frames. It was shown that in this setting even a simple linear CNN structure produces better results than a prediction based on the reversed backward flow. | en |
dc.language.iso | en | de |
dc.rights | info:eu-repo/semantics/openAccess | de |
dc.subject.ddc | 004 | de |
dc.title | CNN-based prediction of optical flow | en |
dc.title.alternative | Neuronale Faltungsnetze zur Vorhersage des Optischen Flusses | de |
dc.type | bachelorThesis | de |
ubs.fakultaet | Informatik, Elektrotechnik und Informationstechnik | de |
ubs.institut | Institut für Visualisierung und Interaktive Systeme | de |
ubs.publikation.seiten | 53 | de |
ubs.publikation.typ | Abschlussarbeit (Bachelor) | de |
Enthalten in den Sammlungen: | 05 Fakultät Informatik, Elektrotechnik und Informationstechnik |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
Bachelorarbeit_Jonathan_Stumber.pdf | 8,85 MB | Adobe PDF | Öffnen/Anzeigen |
Alle Ressourcen in diesem Repositorium sind urheberrechtlich geschützt.