---
OA_type: closed access
_id: '3189'
abstract:
- lang: eng
  text: This paper presents an algorithm capable of real-time separation of foreground
    from background in monocular video sequences. Automatic segmentation of layers
    from colour/contrast or from motion alone is known to be error-prone. Here motion,
    colour and contrast cues are probabilistically fused together with spatial and
    temporal priors to infer layers accurately and efficiently. Central to our algorithm
    is the fact that pixel velocities are not needed, thus removing the need for optical
    flow estimation, with its tendency to error and computational expense. Instead,
    an efficient motion vs non-motion classifier is trained to operate directly and
    jointly on intensity-change and contrast. Its output is then fused with colour
    information. The prior on segmentation is represented by a second order, temporal,
    Hidden Markov Model, together with a spatial MRF favouring coherence except where
    contrast is high. Finally, accurate layer segmentation and explicit occlusion
    detection are efficiently achieved by binary graph cut. The segmentation accuracy
    of the proposed algorithm is quantitatively evaluated with respect to existing
    ground-truth data and found to be comparable to the accuracy of a state of the
    art stereo segmentation algorithm. Fore-ground/background segmentation is demonstrated
    in the application of live background substitution and shown to generate convincingly
    good quality composite video.
article_processing_charge: No
author:
- first_name: Antonio
  full_name: Criminisi, Antonio
  last_name: Criminisi
- first_name: Geoffrey
  full_name: Cross, Geoffrey
  last_name: Cross
- first_name: Andrew
  full_name: Blake, Andrew
  last_name: Blake
- first_name: Vladimir
  full_name: Kolmogorov, Vladimir
  id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
  last_name: Kolmogorov
citation:
  ama: 'Criminisi A, Cross G, Blake A, Kolmogorov V. Bilayer segmentation of live
    video. In: <i>Proceedings of the 2006 IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition - Volume 1</i>. Vol 1. IEEE; 2006:53-60. doi:<a
    href="https://doi.org/10.1109/CVPR.2006.69">10.1109/CVPR.2006.69</a>'
  apa: 'Criminisi, A., Cross, G., Blake, A., &#38; Kolmogorov, V. (2006). Bilayer
    segmentation of live video. In <i>Proceedings of the 2006 IEEE Computer Society
    Conference on Computer Vision and Pattern Recognition - Volume 1</i> (Vol. 1,
    pp. 53–60). New York, NY, United States: IEEE. <a href="https://doi.org/10.1109/CVPR.2006.69">https://doi.org/10.1109/CVPR.2006.69</a>'
  chicago: Criminisi, Antonio, Geoffrey Cross, Andrew Blake, and Vladimir Kolmogorov.
    “Bilayer Segmentation of Live Video.” In <i>Proceedings of the 2006 IEEE Computer
    Society Conference on Computer Vision and Pattern Recognition - Volume 1</i>,
    1:53–60. IEEE, 2006. <a href="https://doi.org/10.1109/CVPR.2006.69">https://doi.org/10.1109/CVPR.2006.69</a>.
  ieee: A. Criminisi, G. Cross, A. Blake, and V. Kolmogorov, “Bilayer segmentation
    of live video,” in <i>Proceedings of the 2006 IEEE Computer Society Conference
    on Computer Vision and Pattern Recognition - Volume 1</i>, New York, NY, United
    States, 2006, vol. 1, pp. 53–60.
  ista: 'Criminisi A, Cross G, Blake A, Kolmogorov V. 2006. Bilayer segmentation of
    live video. Proceedings of the 2006 IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition - Volume 1. CVPR: Computer Vision and Pattern Recognition
    vol. 1, 53–60.'
  mla: Criminisi, Antonio, et al. “Bilayer Segmentation of Live Video.” <i>Proceedings
    of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    - Volume 1</i>, vol. 1, IEEE, 2006, pp. 53–60, doi:<a href="https://doi.org/10.1109/CVPR.2006.69">10.1109/CVPR.2006.69</a>.
  short: A. Criminisi, G. Cross, A. Blake, V. Kolmogorov, in:, Proceedings of the
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    - Volume 1, IEEE, 2006, pp. 53–60.
conference:
  end_date: 2006-06-22
  location: New York, NY, United States
  name: 'CVPR: Computer Vision and Pattern Recognition'
  start_date: 2006-06-17
date_created: 2018-12-11T12:01:54Z
date_published: 2006-07-05T00:00:00Z
date_updated: 2026-09-02T08:41:37Z
day: '05'
doi: 10.1109/CVPR.2006.69
extern: '1'
fulldoi: https://doi.org/10.1109/CVPR.2006.69
intvolume: '         1'
language:
- iso: eng
main_file_link:
- url: http://research.microsoft.com/en-us/um/people/ablake/papers/ablake/criminisi_cvpr06.pdf
month: '07'
oa_version: None
page: 53 - 60
publication: Proceedings of the 2006 IEEE Computer Society Conference on Computer
  Vision and Pattern Recognition - Volume 1
publication_identifier:
  isbn:
  - '0769525970'
  issn:
  - 1063-6919
publication_status: published
publisher: IEEE
publist_id: '3494'
status: public
title: Bilayer segmentation of live video
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 1
year: '2006'
...
---
OA_type: closed access
_id: '3188'
abstract:
- lang: eng
  text: 'We introduce the term cosegmentation which denotes the task of segmenting
    simultaneously the common parts of an image pair. A generative model for cosegmentation
    is presented. Inference in the model leads to minimizing an energy with an MRF
    term encoding spatial coherency and a global constraint which attempts to match
    the appearance histograms of the common parts. This energy has not been proposed
    previously and its optimization is challenging and NP-hard. For this problem a
    novel optimization scheme which we call trust region graph cuts is presented.
    We demonstrate that this framework has the potential to improve a wide range of
    research: Object driven image retrieval, video tracking and segmentation, and
    interactive image editing. The power of the framework lies in its generality,
    the common part can be a rigid/non-rigid object (or scene), observed from different
    viewpoints or even similar objects of the same class.'
article_processing_charge: No
author:
- first_name: Carsten
  full_name: Rother, Carsten
  last_name: Rother
- first_name: Vladimir
  full_name: Kolmogorov, Vladimir
  id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
  last_name: Kolmogorov
- first_name: Thomas
  full_name: Minka, Thomas
  last_name: Minka
- first_name: Andrew
  full_name: Blake, Andrew
  last_name: Blake
citation:
  ama: 'Rother C, Kolmogorov V, Minka T, Blake A. Cosegmentation of image pairs by
    histogram matching - Incorporating a global constraint into MRFs. In: <i>Proceedings
    of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    - Volume 1</i>. IEEE; 2006:993-1000. doi:<a href="https://doi.org/10.1109/CVPR.2006.91">10.1109/CVPR.2006.91</a>'
  apa: 'Rother, C., Kolmogorov, V., Minka, T., &#38; Blake, A. (2006). Cosegmentation
    of image pairs by histogram matching - Incorporating a global constraint into
    MRFs. In <i>Proceedings of the 2006 IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition - Volume 1</i> (pp. 993–1000). New York, NY, United
    States: IEEE. <a href="https://doi.org/10.1109/CVPR.2006.91">https://doi.org/10.1109/CVPR.2006.91</a>'
  chicago: Rother, Carsten, Vladimir Kolmogorov, Thomas Minka, and Andrew Blake. “Cosegmentation
    of Image Pairs by Histogram Matching - Incorporating a Global Constraint into
    MRFs.” In <i>Proceedings of the 2006 IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition - Volume 1</i>, 993–1000. IEEE, 2006. <a href="https://doi.org/10.1109/CVPR.2006.91">https://doi.org/10.1109/CVPR.2006.91</a>.
  ieee: C. Rother, V. Kolmogorov, T. Minka, and A. Blake, “Cosegmentation of image
    pairs by histogram matching - Incorporating a global constraint into MRFs,” in
    <i>Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision
    and Pattern Recognition - Volume 1</i>, New York, NY, United States, 2006, pp.
    993–1000.
  ista: 'Rother C, Kolmogorov V, Minka T, Blake A. 2006. Cosegmentation of image pairs
    by histogram matching - Incorporating a global constraint into MRFs. Proceedings
    of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    - Volume 1. CVPR: Computer Vision and Pattern Recognition, 993–1000.'
  mla: Rother, Carsten, et al. “Cosegmentation of Image Pairs by Histogram Matching
    - Incorporating a Global Constraint into MRFs.” <i>Proceedings of the 2006 IEEE
    Computer Society Conference on Computer Vision and Pattern Recognition - Volume
    1</i>, IEEE, 2006, pp. 993–1000, doi:<a href="https://doi.org/10.1109/CVPR.2006.91">10.1109/CVPR.2006.91</a>.
  short: C. Rother, V. Kolmogorov, T. Minka, A. Blake, in:, Proceedings of the 2006
    IEEE Computer Society Conference on Computer Vision and Pattern Recognition -
    Volume 1, IEEE, 2006, pp. 993–1000.
conference:
  end_date: 2006-06-22
  location: New York, NY, United States
  name: 'CVPR: Computer Vision and Pattern Recognition'
  start_date: 2006-06-17
date_created: 2018-12-11T12:01:54Z
date_published: 2006-07-05T00:00:00Z
date_updated: 2026-09-02T08:39:12Z
day: '05'
doi: 10.1109/CVPR.2006.91
extern: '1'
fulldoi: https://doi.org/10.1109/CVPR.2006.91
language:
- iso: eng
month: '07'
oa_version: None
page: 993 - 1000
publication: Proceedings of the 2006 IEEE Computer Society Conference on Computer
  Vision and Pattern Recognition - Volume 1
publication_identifier:
  isbn:
  - '0769525970'
  issn:
  - 1063-6919
publication_status: published
publisher: IEEE
publist_id: '3493'
status: public
title: Cosegmentation of image pairs by histogram matching - Incorporating a global
  constraint into MRFs
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
year: '2006'
...