Surface Flow from Visual Cues - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Surface Flow from Visual Cues

Benjamin Petit
  • Function : Author
  • PersonId : 863454
Antoine Letouzey
  • Function : Author
  • PersonId : 900968
Edmond Boyer

Abstract

In this paper we study the estimation of dense, instantaneous 3D motion fields over a non-rigidly moving surface observed by multi-camera systems. The motivation arises from multi-camera applications that require motion information, for arbitrary subjects, in order to perform tasks such as surface tracking or segmentation. To this aim, we present a novel framework that allows to efficiently compute dense 3D displacement fields using low level visual cues and geometric constraints. The main contribution is a unified framework that combines flow constraints for small displacements with temporal feature constraints for large displacements and fuses them over the surface using local rigidity constraints. The resulting linear optimization problem allows for variational solutions and fast implementations. Experiments conducted on synthetic and real data demonstrate the respective roles of flow and feature constraints as well as their ability to provide robust surface motion cues when combined.
Fichier principal
Vignette du fichier
surface_flow_from_visual_cues.pdf (1.66 Mo) Télécharger le fichier
Vignette du fichier
FlashKickSceneFlowCst0.png (422.15 Ko) Télécharger le fichier
oral.pdf (17.31 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Other

Dates and versions

inria-00631476 , version 1 (08-03-2012)

Identifiers

Cite

Benjamin Petit, Antoine Letouzey, Edmond Boyer, Jean-Sébastien Franco. Surface Flow from Visual Cues. VMV 2011 - Vision, Modeling and Visualization Workshop, Oct 2011, Berlin, Germany. pp.1-8, ⟨10.2312/PE/VMV/VMV11/001-008⟩. ⟨inria-00631476⟩
403 View
1180 Download

Altmetric

Share

Gmail Facebook X LinkedIn More