Show simple item record

dc.contributor.authorAlexey, Abramov
dc.contributor.authorAksoy, Eren Erdal
dc.contributor.authorDörr, Johannes
dc.contributor.authorWörgötter, Florentin
dc.contributor.authorPauwels, Karl
dc.contributor.authorDellen, Babette
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2010-08-23T09:11:59Z
dc.date.available2010-08-23T09:11:59Z
dc.date.created2010
dc.date.issued2010
dc.identifier.citationAlexey, A. [et al.]. 3d semantic representation of actions from effcient stereo-image-sequence segmentation on GPUs. A: International Symposium 3D Data Processing, Visualization and Transmission. "International Symposium 3D Data Processing, Visualization and Transmission (3DPVT) Edition 5th". Paris: 2010, p. 1-8.
dc.identifier.urihttp://hdl.handle.net/2117/8683
dc.description.abstractA novel real-time framework for model-free stereo-video segmentation and stereo-segment tracking is presented, combining real-time optical flow and stereo with image segmentation running separately on two GPUs. The stereosegment tracking algorithm achieves a frame rate of 23 Hz for regular videos with a frame size of 256 x 320 pixels and nearly real time for stereo videos. The computed stereo segments are used to construct 3D segment graphs, from which main graphs, representing a relevant change in the scene, are extracted, which allow us to represent a movie of e.g. 396 original frames by only 12 graphs, each containing only a small number of nodes, providing a condensed description of the scene while preserving data-intrinsic semantics. Using this method, human activities, e.g., handling of objects, can be encoded in an efficient way. The method has potential applications for manipulation action recognition and learning, and provides a vision-front end for applications in cognitive robotics.
dc.format.extent8 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes
dc.subject.lcshPattern recognition systems
dc.title3d semantic representation of actions from effcient stereo-image-sequence segmentation on GPUs
dc.typeConference report
dc.subject.lemacReconeixement de formes (Informàtica)
dc.subject.inspecClassificació INSPEC::Pattern recognition
dc.relation.publisherversionhttp://campwww.informatik.tu-muenchen.de/3DPVT2010/doku.php?id=acceptedpapers
dc.rights.accessOpen Access
drac.iddocument2634162
dc.description.versionPostprint (published version)
upcommons.citation.authorAlexey, A.; Aksoy , E.; Dörr, J.; Wörgötter , F.; Pauwels, K.; Dellen, B.
upcommons.citation.contributorInternational Symposium 3D Data Processing, Visualization and Transmission
upcommons.citation.pubplaceParis
upcommons.citation.publishedtrue
upcommons.citation.publicationNameInternational Symposium 3D Data Processing, Visualization and Transmission (3DPVT) Edition 5th
upcommons.citation.startingPage1
upcommons.citation.endingPage8


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder