Conference item icon

Conference item

Bayesian estimation of layers from multiple images

Abstract:

When estimating foreground and background layers (or equivalently an alpha matte), it is often the case that pixel measurements contain mixed colours which are a combination of foreground and background. Object boundaries, especially at thin sub-pixel structures like hair, pose a serious problem.


In this paper we present a multiple view algorithm for computing the alpha matte. Using a Bayesian framework, we model each pixel as a combined sample from the foreground and background and compute a MAP estimate to factor the two. The novelties in this work include the incorporation of three different types of priors for enhancing the results in problematic scenes. The priors used are inequality constraints on colour and alpha values, spatial continuity, and the probability distribution of alpha values.


The combination of these priors result in accurate and visually satisfying estimates. We demonstrate the method on real image sequences with varying degrees of geometric and photometric complexity. The output enables virtual objects to be added between the foreground and background layers, and we give examples of this augmentation to the original sequences.

Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1007/3-540-47977-5_32

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author
ORCID:
0000-0002-8945-8573


Publisher:
Springer
Host title:
Computer Vision - ECCV 2002 7th European Conference on Computer Vision, Copenhagen, Denmark, May 28-31, 2002, Proceedings, Part III
Pages:
487-501
Series:
Lecture Notes in Computer Science
Series number:
2352
Publication date:
2002-01-01
Event title:
7th European Conference on Computer Vision (ECCV 2002)
Event location:
Denmark, Copenhagen
Event start date:
2002-05-28
Event end date:
2002-05-31
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
EISBN:
9783540479772
ISBN-10:
3540437460
ISBN-13:
9783540437468


Language:
English
Keywords:
Pubs id:
61962
Local pid:
pubs:61962
Deposit date:
2024-07-26

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP