Motion Cooperation: Smooth Piece-wise Rigid Scene Flow from RGB-D Images

Mariano Jaimez, Mohamed Souiai, Jorg Stuckler, Javier Gonzalez-Jimenez, Daniel Cremers

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

29 Scopus citations

Abstract

We propose a novel joint registration and segmentation approach to estimate scene flow from RGB-D images. Instead of assuming the scene to be composed of a number of independent rigidly-moving parts, we use non-binary labels to capture non-rigid deformations at transitions between the rigid parts of the scene. Thus, the velocity of any point can be computed as a linear combination (interpolation) of the estimated rigid motions, which provides better results than traditional sharp piecewise segmentations. Within a variational framework, the smooth segments of the scene and their corresponding rigid velocities are alternately refined until convergence. A K-means-based segmentation is employed as an initialization, and the number of regions is subsequently adapted during the optimization process to capture any arbitrary number of independently moving objects. We evaluate our approach with both synthetic and real RGB-D images that contain varied and large motions. The experiments show that our method estimates the scene flow more accurately than the most recent works in the field, and at the same time provides a meaningful segmentation of the scene based on 3D motion.

Original languageEnglish
Title of host publicationProceedings - 2015 International Conference on 3D Vision, 3DV 2015
EditorsMichael Brown, Jana Kosecka, Christian Theobalt
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages64-72
Number of pages9
ISBN (Electronic)9781467383325
DOIs
StatePublished - 20 Nov 2015
Event2015 International Conference on 3D Vision, 3DV 2015 - Lyon, France
Duration: 19 Oct 201522 Oct 2015

Publication series

NameProceedings - 2015 International Conference on 3D Vision, 3DV 2015

Conference

Conference2015 International Conference on 3D Vision, 3DV 2015
Country/TerritoryFrance
CityLyon
Period19/10/1522/10/15

Keywords

  • RGB-D
  • motion estimation
  • scene flow
  • smooth segmentation

Fingerprint

Dive into the research topics of 'Motion Cooperation: Smooth Piece-wise Rigid Scene Flow from RGB-D Images'. Together they form a unique fingerprint.

Cite this