Skip to Main content Skip to Navigation
Theses

Scene Flow Estimation from RGBD Images

Abstract : This thesis addresses the problem of reliably recovering a 3D motion field, or scene flow, from a temporal pair of RGBD images. We propose a semi-rigid estimation framework for the robust computation of scene flow, taking advantage of color and depth information, and an alternating variational minimization framework for recovering rigid and non-rigid components of the 3D motion field. Previous attempts to estimate scene flow from RGBD images have extended optical flow approaches without fully exploiting depth data or have formulated the estimation in 3D space disregarding the semi-rigidity of real scenes. We demonstrate that scene flow can be robustly and accurately computed in the image domain by solving for 3D motions consistent with color and depth, encouraging an adjustable combination between local and piecewise rigidity. Additionally, we show that solving for the 3D motion field can be seen as a specific case of a more general estimation problem of a 6D field of rigid motions. Accordingly, we formulate scene flow estimation as the search of an optimal field of twist motions achieving state-of-the-art results.STAR
Complete list of metadatas

Cited literature [81 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01561598
Contributor : Abes Star :  Contact
Submitted on : Thursday, July 13, 2017 - 10:09:06 AM
Last modification on : Thursday, November 19, 2020 - 1:00:01 PM
Long-term archiving on: : Thursday, January 25, 2018 - 1:59:50 AM

File

QUIROGA_SEPULVEDA_2014_archiva...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01561598, version 1

Collections

STAR | CNRS | LIG | UGA

Citation

Julián Quiroga Sepúlveda. Scene Flow Estimation from RGBD Images. Computer Vision and Pattern Recognition [cs.CV]. Université de Grenoble, 2014. English. ⟨NNT : 2014GRENM057⟩. ⟨tel-01561598⟩

Share

Metrics

Record views

895

Files downloads

416