Scene Flow Estimation by Growing Correspondence Seeds - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Scene Flow Estimation by Growing Correspondence Seeds

(1) , (1) , (1)
1

Abstract

A simple seed growing algorithm for estimating scene flow in a stereo setup is presented. Two calibrated and synchronized cameras observe a scene and output a sequence of image pairs. The algorithm simultaneously computes a disparity map between the image pairs and optical flow maps between consecutive images. This, together with calibration data, is an equivalent representation of the 3D scene flow, i.e. a 3D velocity vector is associated with each reconstructed point. The proposed method starts from correspondence seeds and propagates these correspondences to their neighborhood. It is accurate for complex scenes with large motions and produces temporallycoherent stereo disparity and optical flow results. The algorithm is fast due to inherent search space reduction. An explicit comparison with recent methods of spatiotemporal stereo and variational optical and scene flow is provided.
Fichier principal
Vignette du fichier
Cech-CVPR-2011.pdf (2.96 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00590274 , version 1 (14-07-2011)

Identifiers

Cite

Jan Cech, Jordi Sanchez-Riera, Radu Horaud. Scene Flow Estimation by Growing Correspondence Seeds. CVPR 2011 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. pp.3129-3136, ⟨10.1109/CVPR.2011.5995442⟩. ⟨inria-00590274⟩
391 View
928 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More