3d semantic representation of actions from effcient stereo-image-sequence segmentation on GPUs
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/8683
Tipus de documentText en actes de congrés
Data publicació2010
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
A 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.
CitacióAlexey, 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.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
dellen.pdf | 2,238Mb | Visualitza/Obre |