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:
-
-
(Preview, Accepted manuscript, pdf, 1.3MB, Terms of use)
-
- Publisher copy:
- 10.1007/3-540-47977-5_32
Authors
- 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
- Copyright holder:
- Springer-Verlag
- Copyright date:
- 2002
- Rights statement:
- © 2002 Springer-Verlag Berlin Heidelberg
- Notes:
- This paper was presented at the 7th European Conference on Computer Vision (ECCV 2002), 28th-31st May 2002, Copenhagen, Denmark. This is the accepted manuscript version of the article. The final version is available online from Springer at https://dx.doi.org/10.1007/3-540-47977-5_32
If you are the owner of this record, you can report an update to it here: Report update to this record