Skip to Main content Skip to Navigation
New interface
Conference papers

Multi-Camera Scene Flow by Tracking 3-D Points and Surfels

Frédéric Devernay 1 Diana Mateus 1 Matthieu Guilbert 1 
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Scene flow represents the 3-D motion of points in the scene, just as optical flow is related to their 2-D motion in the images. As opposed to classical methods which compute scene flow from optical flow, we propose to compute it by tracking 3-D points and surface elements (surfels) in a multi-camera setup (at least two cameras are needed). Two methods are proposed: in the first one, the translation of each 3-D point is found by matching the neighborhoods of its 2-D projections in each camera between two time steps; in the second one, the full pose of a surfel is recovered by matching the image of its projection with a texture template attached to the surfel, and visibility changes caused by occlusion or rotation of surfels are handled. Both methods detect lost or untrackable points and surfels. They were designed for real-time execution and can be used for fast extraction of scene flow from multi-camera sequences.
Document type :
Conference papers
Complete list of metadata
Contributor : Frédéric Devernay Connect in order to contact the contributor
Submitted on : Tuesday, March 11, 2008 - 12:13:29 PM
Last modification on : Thursday, March 10, 2022 - 6:30:04 PM
Long-term archiving on: : Thursday, May 20, 2010 - 9:50:17 PM


Publisher files allowed on an open archive




Frédéric Devernay, Diana Mateus, Matthieu Guilbert. Multi-Camera Scene Flow by Tracking 3-D Points and Surfels. International Conference on Computer Vision and Pattern Recognition, 2006, New York, United States. pp.2203- 2212, ⟨10.1109/CVPR.2006.194⟩. ⟨inria-00262285⟩



Record views


Files downloads