Scene Flow from Depth and Color Images - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Scene Flow from Depth and Color Images

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

Abstract

In this paper we consider the problem of estimating a 3D motion field using multiple cameras. In particular, we focus on the situation where a depth camera and one or more color cameras are available, a common situation with recent composite sensors such as the Kinect. In this case, geometric information from depth maps can be combined with intensity variations in color images in order to estimate smooth and dense 3D motion fields. We propose a unified framework for this purpose, that can handle both arbitrary large motions and sub-pixel displacements. The estimation is cast as a linear optimization problem that can be solved very efficiently. The novelty with respect to existing scene flow approaches is that it takes advantage of the geometric information provided by the depth camera to define a surface domain over which photometric constraints can be consistently integrated in 3D. Experiments on real and synthetic data provide both qualitative and quantitative results that demonstrate the interest of the approach.
Fichier principal
Vignette du fichier
main.pdf (680.57 Ko) Télécharger le fichier
Vignette du fichier
overview.jpg (264.17 Ko) Télécharger le fichier
bmvc11_poster.pdf (3.35 Mo) Télécharger le fichier
extended_abstract.pdf (2.79 Mo) Télécharger le fichier
Vignette du fichier
res_0.png (29.2 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Format : Other
Format : Other
Format : Figure, Image
Loading...

Dates and versions

inria-00616353 , version 1 (22-08-2011)

Identifiers

Cite

Antoine Letouzey, Benjamin Petit, Edmond Boyer. Scene Flow from Depth and Color Images. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. pp.46:1-11, ⟨10.5244/C.25.46⟩. ⟨inria-00616353⟩
488 View
1395 Download

Altmetric

Share

Gmail Facebook X LinkedIn More