Temporally Consistent Motion Segmentation from RGB-D Video

Bertholet, Peter-Immanuel; Zwicker, Matthias (2016). Temporally Consistent Motion Segmentation from RGB-D Video Cornell University Library

[img]
Preview
Text
1608.04642v1.pdf - Published Version
Available under License Publisher holds Copyright.

Download (6MB) | Preview

We present a method for temporally consistent motion segmentation from RGB-D videos assuming a piecewise rigid motion model. We formulate global energies over entire RGB-D sequences in terms of the segmentation of each frame into a number of objects, and the rigid motion of each object through the sequence. We develop a novel initialization procedure that clusters feature tracks obtained from the RGB data by leveraging the depth information.We minimize the energy using a coordinate descent approach that includes novel techniques to assemble object motion hypotheses. A main benefit of our approach is that it enables us to fuse consistently labeled object segments from all RGB-D frames of an input sequence into individual 3D object reconstructions.

Item Type: Report (Report)
Division/Institute: 08 Faculty of Science > Institute of Computer Science (INF) > Computer Graphics Group (CGG)
08 Faculty of Science > Institute of Computer Science (INF)
UniBE Contributor: Bertholet, Peter-Immanuel and Zwicker, Matthias
Subjects: 000 Computer science, knowledge & systems
500 Science > 510 Mathematics
Publisher: Cornell University Library
Language: English
Submitter: Matthias Zwicker
Date Deposited: 22 Aug 2016 10:58
Last Modified: 22 Aug 2016 10:58
ArXiv ID: 1608.04642
BORIS DOI: 10.7892/boris.86116
URI: http://boris.unibe.ch/id/eprint/86116

Actions (login required)

Edit item Edit item
Provide Feedback