Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Marzat, Julien | |
dc.contributor.author | Dumortier, Yann | |
dc.contributor.author | Ducrot, Andre | |
dc.contributor.editor | Chen, Min | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2014-03-26T12:04:15Z | |
dc.date.available | 2014-03-26T12:04:15Z | |
dc.date.issued | 2009 | |
dc.identifier.citation | WSCG '2009: Full Papers Proceedings: The 17th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision in co-operation with EUROGRAPHICS: University of West Bohemia Plzen, Czech Republic, February 2 - 5, 2009, p. 105-112. | en |
dc.identifier.isbn | 978-80-86943-93-0 | |
dc.identifier.uri | http://wscg.zcu.cz/WSCG2009/Papers_2009/!_WSCG2009_Full_final.zip | |
dc.identifier.uri | http://hdl.handle.net/11025/10895 | |
dc.description.abstract | A large number of processes in computer vision are based on the image motion measurement, which is the projection of the real displacement on the focal plane. Such a motion is currently approximated by the visual displacement field, called optical flow. Nowadays, a lot of different methods are commonly used to estimate it, but a good trade-off between execution time and accuracy is hard to achieve with standard integrations. This paper tackles the problem by proposing a parallel implementation of the well-known pyramidal algorithm of Lucas & Kanade, in a Graphics Processing Unit (GPU). It is programmed using the Compute Unified Device Architecture from NVIDIA corporation, to compute a dense and accurate velocity field at about 15 Hz with a 640 480 image definition. | en |
dc.format | 8 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | cs |
dc.relation.ispartofseries | WSCG '2009: Full Papers Proceedings | en |
dc.rights | © Václav Skala - UNION Agency | en |
dc.subject | zpracování obrazu | cs |
dc.subject | monokulární vidění | cs |
dc.subject | optický tok | cs |
dc.subject | paralelní zpracování | cs |
dc.subject | grafický procesor | cs |
dc.title | Real-Time Dense and Accurate Parallel Optical Flow using CUDA | en |
dc.type | konferenční příspěvek | cs |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.subject.translated | image processing | en |
dc.subject.translated | monocular vision | en |
dc.subject.translated | optical flow | en |
dc.subject.translated | parallel processing | en |
dc.subject.translated | graphic processing | en |
dc.type.status | Peer-reviewed | en |
dc.type.driver | info:eu-repo/semantics/conferenceObject | en |
dc.type.driver | info:eu-repo/semantics/publishedVersion | en |
Vyskytuje se v kolekcích: | WSCG '2009: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
Marzat.pdf | Plný text | 4,02 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/10895
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.