University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Probabilistic Motion Diffusion of Labeling Priors for Coherent Video Segmentation

Wang, Tinghuai and Collomosse, John (2012) Probabilistic Motion Diffusion of Labeling Priors for Coherent Video Segmentation IEEE Transactions on Multimedia, 14 (2). pp. 389-400. ISSN 1520-9210

[img]
Preview
PDF
Wang-TMM-2012.pdf - Accepted Version

Download (28Mb)

Abstract

We present a robust algorithm for temporally coherent video segmentation. Our approach is driven by multi-label graph cut applied to successive frames, fusing information from the current frame with an appearance model and labelling priors propagated forwarded from past frames. We propagate using a novel motion diffusion model, producing a per-pixel motion distribution that mitigates against cumulative estimation errors inherent in systems adopting `hard' decisions on pixel motion at each frame. Further, we encourage spatial coherence by imposing label consistency constraints within image regions (super-pixels) obtained via a bank of unsupervised frame segmentations, such as mean-shift. We demonstrate quantitative improvements in accuracy over state-of-the-art methods on a variety of sequences exhibiting clutter and agile motion, adopting the Berkeley methodology for our comparative evaluation.

Item Type: Article
Additional Information: © 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related URLs:
Divisions: Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Depositing User: John Collomosse
Date Deposited: 24 Apr 2012 10:18
Last Modified: 23 Sep 2013 19:18
URI: http://epubs.surrey.ac.uk/id/eprint/289601

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800