Local/Global Scene Flow Estimation

Julian Quiroga 1, 2 Frédéric Devernay 1, * James L. Crowley 1
* Corresponding author
1 PRIMA - Perception, recognition and integration for observation of activity
Inria Grenoble - Rhône-Alpes, UJF - Université Joseph Fourier - Grenoble 1, INPG - Institut National Polytechnique de Grenoble , CNRS - Centre National de la Recherche Scientifique : UMR5217
Abstract : The scene flow describes the 3D motion of every point in a scene between two time steps. We present a novel method to estimate a dense scene flow using intensity and depth data. It is well known that local methods are more robust under noise while global techniques yield dense motion estimation. We combine local and global constraints to solve for the scene flow in a variational framework. An adaptive TV (Total Variation) regularization is used to preserve motion discontinuities. Besides, we constrain the motion using a set of 3D correspondences to deal with large displacements. In the experimentation our approach outperforms previous scene flow from intensity and depth methods in terms of accuracy.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-00829515
Contributor : Frédéric Devernay <>
Submitted on : Monday, June 3, 2013 - 2:17:42 PM
Last modification on : Saturday, June 2, 2018 - 1:24:19 AM
Long-term archiving on : Wednesday, September 4, 2013 - 4:13:18 AM

File

quiroga-lgsceneflow-icip2013.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00829515, version 1

Collections

Citation

Julian Quiroga, Frédéric Devernay, James L. Crowley. Local/Global Scene Flow Estimation. ICIP - IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. ⟨hal-00829515⟩

Share

Metrics

Record views

1129

Files downloads

797