Integrated spatial and frequency domain 2D motion segmentation and estimation

Alexia Briassouli; Narendra Ahuja

doi:10.1109/ICCV.2005.123

Integrated spatial and frequency domain 2D motion segmentation and estimation

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

Abstract

A video containing multiple objects In rotational and translational motion is analyzed through a combination of spatial and frequency domain representations. It is argued that the combined analysis can take advantage of the strengths of both representations. Initial estimates of constant, as well as time-varying, translation and rotation velocities are obtained from frequency analysis. Improved motion estimates and motion segmentation for the case of translation are achieved by integrating spatial and Fourier domain information. For combined rotational and translational motions, the frequency representation is used for motion estimation, but only spatial information can be used to separate and extract the independently moving objects. The proposed algorithms are tested on synthetic and real videos.

Original language	English (US)
Title of host publication	Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages	244-250
Number of pages	7
DOIs	https://doi.org/10.1109/ICCV.2005.123
State	Published - 2005
Event	Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China Duration: Oct 17 2005 → Oct 20 2005

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	I

Other

Other	Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Country/Territory	China
City	Beijing
Period	10/17/05 → 10/20/05

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Online availability

10.1109/ICCV.2005.123

Library availability

Discover UIUC Full Text

Cite this

Integrated spatial and frequency domain 2D motion segmentation and estimation. / Briassouli, Alexia; Ahuja, Narendra.
Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. 2005. p. 244-250 1541263 (Proceedings of the IEEE International Conference on Computer Vision; Vol. I).

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

Briassouli, A & Ahuja, N 2005, Integrated spatial and frequency domain 2D motion segmentation and estimation. in Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005., 1541263, Proceedings of the IEEE International Conference on Computer Vision, vol. I, pp. 244-250, Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, 10/17/05. https://doi.org/10.1109/ICCV.2005.123

@inproceedings{09d27cc79fc742cd8f59146373887d70,

title = "Integrated spatial and frequency domain 2D motion segmentation and estimation",

abstract = "A video containing multiple objects In rotational and translational motion is analyzed through a combination of spatial and frequency domain representations. It is argued that the combined analysis can take advantage of the strengths of both representations. Initial estimates of constant, as well as time-varying, translation and rotation velocities are obtained from frequency analysis. Improved motion estimates and motion segmentation for the case of translation are achieved by integrating spatial and Fourier domain information. For combined rotational and translational motions, the frequency representation is used for motion estimation, but only spatial information can be used to separate and extract the independently moving objects. The proposed algorithms are tested on synthetic and real videos.",

author = "Alexia Briassouli and Narendra Ahuja",

year = "2005",

doi = "10.1109/ICCV.2005.123",

language = "English (US)",

isbn = "076952334X",

series = "Proceedings of the IEEE International Conference on Computer Vision",

pages = "244--250",

booktitle = "Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005",

}

TY - GEN

T1 - Integrated spatial and frequency domain 2D motion segmentation and estimation

AU - Briassouli, Alexia

AU - Ahuja, Narendra

PY - 2005

Y1 - 2005

N2 - A video containing multiple objects In rotational and translational motion is analyzed through a combination of spatial and frequency domain representations. It is argued that the combined analysis can take advantage of the strengths of both representations. Initial estimates of constant, as well as time-varying, translation and rotation velocities are obtained from frequency analysis. Improved motion estimates and motion segmentation for the case of translation are achieved by integrating spatial and Fourier domain information. For combined rotational and translational motions, the frequency representation is used for motion estimation, but only spatial information can be used to separate and extract the independently moving objects. The proposed algorithms are tested on synthetic and real videos.

AB - A video containing multiple objects In rotational and translational motion is analyzed through a combination of spatial and frequency domain representations. It is argued that the combined analysis can take advantage of the strengths of both representations. Initial estimates of constant, as well as time-varying, translation and rotation velocities are obtained from frequency analysis. Improved motion estimates and motion segmentation for the case of translation are achieved by integrating spatial and Fourier domain information. For combined rotational and translational motions, the frequency representation is used for motion estimation, but only spatial information can be used to separate and extract the independently moving objects. The proposed algorithms are tested on synthetic and real videos.

UR - http://www.scopus.com/inward/record.url?scp=33745950309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745950309&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2005.123

DO - 10.1109/ICCV.2005.123

M3 - Conference contribution

AN - SCOPUS:33745950309

SN - 076952334X

SN - 9780769523347

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 244

EP - 250

BT - Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

T2 - Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

Y2 - 17 October 2005 through 20 October 2005

ER -

Integrated spatial and frequency domain 2D motion segmentation and estimation

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this