Multiscale segmentation by combining motion and intensity cues

Meirav Galun; Alexander Apartsin; Ronen Basri

doi:10.1109/CVPR.2005.244

Multiscale segmentation by combining motion and intensity cues

Meirav Galun, Alexander Apartsin, Ronen Basri

Weizmann Institute of Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguities and reach reliable estimates of the motion. In addition, as the aggregation process proceeds and larger aggregates are identified it employs a progressively more complex model to describe the motion. In particular, we proceed by recovering translational motion at fine levels, through affine transformation at intermediate levels, to 3D motion (described by a fundamental matrix) at the coarsest levels. Finally, the method is integrated with a segmentation method that uses intensity cues. We further demonstrate the utility of the method on both random dot and real motion sequences.

Original language	English
Title of host publication	Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Publisher	IEEE Computer Society
Pages	256-263
Number of pages	8
ISBN (Print)	0769523722, 9780769523729
DOIs	https://doi.org/10.1109/CVPR.2005.244
State	Published - 2005
Externally published	Yes
Event	2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States Duration: 20 Jun 2005 → 25 Jun 2005

Publication series

Name	Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Volume	I

Conference

Conference	2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Country/Territory	United States
City	San Diego, CA
Period	20/06/05 → 25/06/05

Access to Document

10.1109/CVPR.2005.244

Cite this

Galun, M., Apartsin, A., & Basri, R. (2005). Multiscale segmentation by combining motion and intensity cues. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 (pp. 256-263). Article 1467276 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. I). IEEE Computer Society. https://doi.org/10.1109/CVPR.2005.244

Galun, Meirav ; Apartsin, Alexander ; Basri, Ronen. / Multiscale segmentation by combining motion and intensity cues. Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society, 2005. pp. 256-263 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005).

@inproceedings{4ec0f012f3274848badce921c58ec7c7,

title = "Multiscale segmentation by combining motion and intensity cues",

abstract = "We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguities and reach reliable estimates of the motion. In addition, as the aggregation process proceeds and larger aggregates are identified it employs a progressively more complex model to describe the motion. In particular, we proceed by recovering translational motion at fine levels, through affine transformation at intermediate levels, to 3D motion (described by a fundamental matrix) at the coarsest levels. Finally, the method is integrated with a segmentation method that uses intensity cues. We further demonstrate the utility of the method on both random dot and real motion sequences.",

author = "Meirav Galun and Alexander Apartsin and Ronen Basri",

year = "2005",

doi = "10.1109/CVPR.2005.244",

language = "אנגלית",

isbn = "0769523722",

series = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",

publisher = "IEEE Computer Society",

pages = "256--263",

booktitle = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",

address = "ארצות הברית",

note = "2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 ; Conference date: 20-06-2005 Through 25-06-2005",

}

Galun, M, Apartsin, A & Basri, R 2005, Multiscale segmentation by combining motion and intensity cues. in Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005., 1467276, Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. I, IEEE Computer Society, pp. 256-263, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, United States, 20/06/05. https://doi.org/10.1109/CVPR.2005.244

Multiscale segmentation by combining motion and intensity cues. / Galun, Meirav; Apartsin, Alexander; Basri, Ronen.
Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society, 2005. p. 256-263 1467276 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. I).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multiscale segmentation by combining motion and intensity cues

AU - Galun, Meirav

AU - Apartsin, Alexander

AU - Basri, Ronen

PY - 2005

Y1 - 2005

N2 - We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguities and reach reliable estimates of the motion. In addition, as the aggregation process proceeds and larger aggregates are identified it employs a progressively more complex model to describe the motion. In particular, we proceed by recovering translational motion at fine levels, through affine transformation at intermediate levels, to 3D motion (described by a fundamental matrix) at the coarsest levels. Finally, the method is integrated with a segmentation method that uses intensity cues. We further demonstrate the utility of the method on both random dot and real motion sequences.

AB - We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguities and reach reliable estimates of the motion. In addition, as the aggregation process proceeds and larger aggregates are identified it employs a progressively more complex model to describe the motion. In particular, we proceed by recovering translational motion at fine levels, through affine transformation at intermediate levels, to 3D motion (described by a fundamental matrix) at the coarsest levels. Finally, the method is integrated with a segmentation method that uses intensity cues. We further demonstrate the utility of the method on both random dot and real motion sequences.

UR - http://www.scopus.com/inward/record.url?scp=24644456975&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2005.244

DO - 10.1109/CVPR.2005.244

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:24644456975

SN - 0769523722

SN - 9780769523729

T3 - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

SP - 256

EP - 263

BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

PB - IEEE Computer Society

T2 - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

Y2 - 20 June 2005 through 25 June 2005

ER -

Galun M, Apartsin A, Basri R. Multiscale segmentation by combining motion and intensity cues. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society. 2005. p. 256-263. 1467276. (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005). doi: 10.1109/CVPR.2005.244

Multiscale segmentation by combining motion and intensity cues

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this