Conference item
Learning layered motion segmentations of video
- Abstract:
- We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, which consist of one or more segments. Included in the model are the effects of image projection, lighting, and motion blur. The two main contributions of our method are: (i) A novel algorithm for obtaining the initial estimate of the model using efficient loopy belief propagation; (ii) Using αβ-swap and α-expansion algorithms, which guarantee a strong local minima, for refining the initial estimate. Results are presented on several classes of objects with different types of camera motion. We compare our method with the state of the art and demonstrate significant improvements. © 2005 IEEE.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 768.0KB, Terms of use)
-
- Publisher copy:
- 10.1109/iccv.2005.138
Authors
- Publisher:
- IEEE
- Host title:
- Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
- Volume:
- 1
- Pages:
- 1-8
- Publication date:
- 2005-12-05
- Event title:
- Tenth IEEE International Conference on Computer Vision (ICCV'05)
- Event location:
- Beijing, China
- Event start date:
- 2005-10-17
- Event end date:
- 2005-10-21
- DOI:
- EISSN:
-
2380-7504
- ISSN:
-
1550-5499
- ISBN-10:
- 076952334X
- ISBN-13:
- 9780769523347
- Language:
-
English
- Pubs id:
-
61882
- Local pid:
-
pubs:61882
- Deposit date:
-
2024-06-06
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2005
- Rights statement:
- © 2005 IEEE
- Notes:
- This is the accepted manuscript version of the paper. The final version is available online from IEEE at https://dx.doi.org/10.1109/iccv.2005.138
If you are the owner of this record, you can report an update to it here: Report update to this record