Single image 3D human pose estimation from noisy observations
Cita com:
hdl:2117/17353
Tipus de documentText en actes de congrés
Data publicació2012
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
ProjecteINTELLACT - Intelligent observation and execution of Actions and manipulations (EC-FP7-269959)
Abstract
Markerless 3D human pose detection from a single image is a severely underconstrained problem because different 3D poses can have similar image projections. In order to handle this ambiguity, current approaches rely on prior shape models that can only be correctly adjusted if 2D image features are accurately detected. Unfortunately, although current 2D part detector algorithms have shown promising results, they are not yet accurate enough to guarantee a complete disambiguation of the 3D inferred shape.
In this paper, we introduce a novel approach for estimating 3D human pose even when observations are noisy. We propose a stochastic sampling strategy to propagate
the noise from the image plane to the shape space. This provides a set of ambiguous 3D shapes, which are virtually undistinguishable from their image projections. Disambiguation is then achieved by imposing kinematic constraints that guarantee the resulting pose resembles a 3D
human shape. We validate the method on a variety of situations in which state-of-the-art 2D detectors yield either inaccurate estimations or partly miss some of the body parts.
CitacióSimo, E. [et al.]. Single image 3D human pose estimation from noisy observations. A: IEEE Conference on Computer Vision and Pattern Recognition. "Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition". Providence: 2012, p. 2673-2680.
Versió de l'editorhttp://dx.doi.org/10.1109/CVPR.2012.6247988
Col·leccions
- IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [576]
- VIS - Visió Artificial i Sistemes Intel·ligents - Ponències/Comunicacions de congressos [292]
- ROBiri - Grup de Percepció i Manipulació Robotitzada de l'IRI - Ponències/Comunicacions de congressos [252]
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
1353-Single-Ima ... rom-Noisy-Observations.pdf | 4,789Mb | Visualitza/Obre |