Efficient computation of the most probable motion from fuzzy correspondences

M. Ben-Ezra; S. Peleg; M. Werman

doi:10.1109/ACV.1998.732853

Efficient computation of the most probable motion from fuzzy correspondences

M. Ben-Ezra, S. Peleg, M. Werman

The Rachel and Selim Benin School of Engineering and Computer Science

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

4 Scopus citations

Abstract

An algorithm is presented for finding the most probable image motion between two images from fuzzy point correspondences. In fuzzy correspondence a point in one image is assigned to a region in the other image. Such a region can be line (aperture effect) or a convex polygon. Noise and outliers are always present, and points may belong to different motions. The presented algorithm, which uses linear programming, recovers the motion parameters and performs outlier rejection and motion-segmentation at the same time. The linear program computes the global optimum without a need for initial guess.

Original language	English
Title of host publication	Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	22-27
Number of pages	6
ISBN (Electronic)	0818686065, 9780818686061
DOIs	https://doi.org/10.1109/ACV.1998.732853
State	Published - 1998
Event	4th IEEE Workshop on Applications of Computer Vision, WACV 1998 - Princeton, United States Duration: 19 Oct 1998 → 21 Oct 1998

Publication series

Name	Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998
Volume	1998-October

Conference

Conference	4th IEEE Workshop on Applications of Computer Vision, WACV 1998
Country/Territory	United States
City	Princeton
Period	19/10/98 → 21/10/98

Bibliographical note

Publisher Copyright:
© 1998 IEEE.

Access to Document

10.1109/ACV.1998.732853

Cite this

Ben-Ezra, M., Peleg, S., & Werman, M. (1998). Efficient computation of the most probable motion from fuzzy correspondences. In Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998 (pp. 22-27). Article 732853 (Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998; Vol. 1998-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACV.1998.732853

@inproceedings{1c296b04a1ee4eb5bbfda59400f7977e,

title = "Efficient computation of the most probable motion from fuzzy correspondences",

abstract = "An algorithm is presented for finding the most probable image motion between two images from fuzzy point correspondences. In fuzzy correspondence a point in one image is assigned to a region in the other image. Such a region can be line (aperture effect) or a convex polygon. Noise and outliers are always present, and points may belong to different motions. The presented algorithm, which uses linear programming, recovers the motion parameters and performs outlier rejection and motion-segmentation at the same time. The linear program computes the global optimum without a need for initial guess.",

author = "M. Ben-Ezra and S. Peleg and M. Werman",

note = "Publisher Copyright: {\textcopyright} 1998 IEEE.; 4th IEEE Workshop on Applications of Computer Vision, WACV 1998 ; Conference date: 19-10-1998 Through 21-10-1998",

year = "1998",

doi = "10.1109/ACV.1998.732853",

language = "אנגלית",

series = "Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "22--27",

booktitle = "Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998",

address = "ארצות הברית",

}

Ben-Ezra, M, Peleg, S & Werman, M 1998, Efficient computation of the most probable motion from fuzzy correspondences. in Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998., 732853, Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998, vol. 1998-October, Institute of Electrical and Electronics Engineers Inc., pp. 22-27, 4th IEEE Workshop on Applications of Computer Vision, WACV 1998, Princeton, United States, 19/10/98. https://doi.org/10.1109/ACV.1998.732853

Efficient computation of the most probable motion from fuzzy correspondences. / Ben-Ezra, M.; Peleg, S.; Werman, M.
Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998. Institute of Electrical and Electronics Engineers Inc., 1998. p. 22-27 732853 (Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998; Vol. 1998-October).

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

TY - GEN

T1 - Efficient computation of the most probable motion from fuzzy correspondences

AU - Ben-Ezra, M.

AU - Peleg, S.

AU - Werman, M.

PY - 1998

Y1 - 1998

N2 - An algorithm is presented for finding the most probable image motion between two images from fuzzy point correspondences. In fuzzy correspondence a point in one image is assigned to a region in the other image. Such a region can be line (aperture effect) or a convex polygon. Noise and outliers are always present, and points may belong to different motions. The presented algorithm, which uses linear programming, recovers the motion parameters and performs outlier rejection and motion-segmentation at the same time. The linear program computes the global optimum without a need for initial guess.

AB - An algorithm is presented for finding the most probable image motion between two images from fuzzy point correspondences. In fuzzy correspondence a point in one image is assigned to a region in the other image. Such a region can be line (aperture effect) or a convex polygon. Noise and outliers are always present, and points may belong to different motions. The presented algorithm, which uses linear programming, recovers the motion parameters and performs outlier rejection and motion-segmentation at the same time. The linear program computes the global optimum without a need for initial guess.

UR - http://www.scopus.com/inward/record.url?scp=84945259145&partnerID=8YFLogxK

U2 - 10.1109/ACV.1998.732853

DO - 10.1109/ACV.1998.732853

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

AN - SCOPUS:84945259145

T3 - Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998

SP - 22

EP - 27

BT - Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998

Y2 - 19 October 1998 through 21 October 1998

ER -

Ben-Ezra M, Peleg S, Werman M. Efficient computation of the most probable motion from fuzzy correspondences. In Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998. Institute of Electrical and Electronics Engineers Inc. 1998. p. 22-27. 732853. (Proceedings - 4th IEEE Workshop on Applications of Computer Vision, WACV 1998). doi: 10.1109/ACV.1998.732853

Efficient computation of the most probable motion from fuzzy correspondences

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this