loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Sebastien Poullot 1 and Shin'Ichi Satoh 2

Affiliations: 1 NII and JFLI, Japan ; 2 NII and University of Tokyo, Japan

ISBN: 978-989-758-004-8

Keyword(s): Video Segmentation, Points of Interest, Outliers Removal, Frame Alignment, Motion M-layer, GrabCut.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Image and Video Analysis ; Motion, Tracking and Stereo Vision ; Optical Flow and Motion Analyses ; Segmentation and Grouping

Abstract: This paper introduces VabCut, a video extension of GrabCut, an original unsupervised solution to tackle the video foreground object segmentation task. Vabcut works on an extension of the RGB colour domain to RGBM, where M is the motion. It requires a prior step: the computation of the motion layer (M-layer) of the frame to segment. In order to compute this layer we propose to intersect the frame to segment with N temporally close aligned frames. This paper also introduces a new iterative and collaborative method for an optimal frame alignment, based on points of interest and RANSAC, which automatically discards outliers and refines the homographies in turns. The whole method is fully automatic and can handle standard video, i.e. not professional, shaky, blurry or else. We tested VabCut on the SegTrack 2011 benchmark, and demonstrated its effectiveness, it especially outperforms the state of the art methods while being faster.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.172.100.232

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Poullot, S. and Satoh, S. (2014). VabCut: A Video Extension of GrabCut for Unsupervised Video Foreground Object Segmentation.In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 362-371. DOI: 10.5220/0004677103620371

@conference{visapp14,
author={Sebastien Poullot. and Shin'Ichi Satoh.},
title={VabCut: A Video Extension of GrabCut for Unsupervised Video Foreground Object Segmentation},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={362-371},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004677103620371},
isbn={978-989-758-004-8},
}

TY - CONF

JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - VabCut: A Video Extension of GrabCut for Unsupervised Video Foreground Object Segmentation
SN - 978-989-758-004-8
AU - Poullot, S.
AU - Satoh, S.
PY - 2014
SP - 362
EP - 371
DO - 10.5220/0004677103620371

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.