Carregant...
Carregant...

Vés al contingut (premeu Retorn)

A bayesian approach to simultaneously recover camera pose and non-rigid shape from monocular images

Autor
Moreno-Noguer, F.; Porta, J.
Tipus d'activitat
Article en revista
Revista
Image and vision computing
Data de publicació
2016
Volum
52
Pàgina inicial
141
Pàgina final
153
DOI
https://doi.org/10.1016/j.imavis.2016.05.012 Obrir en finestra nova
Projecte finançador
DPI2014-57220-C2-2-P RobCab: Control strategies for cable-driven robot for low-gravity simulation
I-DRESS: Assistive interactive robotic system for support in dressing - PCIN-2015-147
RobInstruct: Instructing robots using natural communication skills - TIN2014-58178-R
Repositori
http://hdl.handle.net/2117/104426 Obrir en finestra nova
URL
http://www.sciencedirect.com/science/article/pii/S0262885616300981 Obrir en finestra nova
Resum
In this paper we bring the tools of the Simultaneous Localization and Map Building (SLAM) problem from a rigid to a deformable domain and use them to simultaneously recover the 3D shape of non-rigid surfaces and the sequence of poses of a moving camera. Under the assumption that the surface shape may be represented as a weighted sum of deformation modes, we show that the problem of estimating the modal weights along with the camera poses, can be probabilistically formulated as a maximum a poster...
Citació
Moreno-Noguer, F., Porta, J.M. A bayesian approach to simultaneously recover camera pose and non-rigid shape from monocular images. "Image and vision computing", 2016, vol. 52, p. 141-153.
Paraules clau
Bayesian belief networks, Deformable surfaces, Pose estimation, Robots, SLAM
Grup de recerca
KRD - Cinemàtica i Disseny de Robots
ROBiri - Grup de Robòtica de l'IRI