Please use this identifier to cite or link to this item:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

3d semantic representation of actions from efficient stereo-image-sequence segmentation on GPUs

AuthorsAbramov, Alexey; Aksoy, Eren Erdal; Dörr, Johannes; Wörgötter, Florentin; Pauwels, Karl; Dellen, Babette CSIC
KeywordsPattern recognition
Issue Date2010
Citation3DPVT 2010
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.
DescriptionTrabajo presentado al 5th International Symposium 3D Data Processing, Visualization and Transmission celebrado en París (Francia) del 17 al 20 de mayo de 2010.
Appears in Collections:(IRII) Comunicaciones congresos

Files in This Item:
File Description SizeFormat
3d semantic representation.pdf2,34 MBAdobe PDFThumbnail
Show full item record
Review this work

Page view(s)

checked on May 23, 2022


checked on May 23, 2022

Google ScholarTM


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.